• Attack-Related
  • Adversarial Attack
    • Survey
    • Attack-WhiteBox
    • Attack-BlackBox
    • Defense-Robustness
    • Defense-Detection
    • Defense-Input transformation
    • Attack-others
    • Certified Robustness
  • Backdoor Attack
    • Survey
    • Attack - Data poisoning
    • Attack - not Data poisoning
    • Attack - others
    • Defense
  • Data Poisoning
  • Hardware Fault Attack
    • Preliminaries
    • Applications
• Privacy-Related
  • Survey
  • Data Reconstruction
  • Membership Inference Attack
  • Property Inference Attack
  • Others
• Fairness & Bias
  • NLP
• Machine Learning Related
  • Fingerprint
    • Model Fingerprint
    • Dataset Fingerprint
  • Watermarking
    • Model Watermarking
    • Dataset Watermarking
  • Machine Unlearning
  • Theoretical Analysis
  • Model Hiding
  • Model Design
  • For Effectiveness
    • Quantization
    • Dynamic NN
      • Security-related
  • Neural Network Interpretability
    • Analysis
    • Attack
    • Defense
• DNN Application
  • GAN & AE
  • Transformer
    • Transformer in Computer Vision
  • Reinforcement Learning
    • Design
      • Basic
      • Multi-Agents
    • Adversarial Attack on RL
    • Others
  • Person Re-identification
    • Survey
    • Toolbox
    • Design
    • Adversarial Attack on ReID
  • Face Recognition
    • Survey
    • Anti FR
• Mathematics
  • Probabilistic Graphical Model
  • Convex Optimization
  • Manifold
  • Learning Theory
  • Causal Inference
  • others

Table of contents generated with markdown-toc

• 2018 IEEE ACCESS Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• 2020 Engineering Adversarial Attacks and Defenses in Deep Learning
• 2021 arxiv Adversarial Example Detection for DNN Models: A Review and Experimental Comparison
• 2021 arxiv Advances in adversarial attacks and defenses in computer vision: A survey

• 2014 ICLR Intriguing properties of neural networks
• 2015 ICLR FGSM Explaining and harnessing adversarial examples
• 2016 S&P JSMA The Limitations of Deep Learning in Adversarial Settings
• 2016 CVPR DeepFool: a simple and accurate method to fool deep neural networks
• 2017 ICLR targeted FGSM Adversarial Machine Learning at Scale
• 2017 ICLR BIM&ICLM Adversarial examples in the physical world
• 2017 S&P C&W Towards Evaluating the Robustness of Neural Networks
• 2017 CVPR Universal adversarial perturbations
• 2018 ICLR PGDTowards Deep Learning Models Resistant to Adversarial Attacks
• 2018 IEEE TECV One-pixel attack One pixel attack for fooling deep neural networks
• 2018 AAAI Adversarial Transformation Networks: Learning to Generate Adversarial Examples
• 2018 CVPR MI-FGSMBoosting Adversarial Attacks With Momentum
• 2018 ICML Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples

• 2017 CCS Practical Black-Box Attacks against Machine Learning

• 2016 arXivDelving into Transferable Adversarial Examples and Black-box Attacks

• 2018 ICDM Query-Efficient Black-Box Attack by Active Learning

• 2019 ICLR Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attacks

• 2020 CVPR Boosting the Transferability of Adversarial Samples via Attention

• 2020 ICLR Skip Connections Matter: On the Transferability of Adversarial Examples Generated with ResNets

• 2020 NeurIPS Backpropagating Linearly Improves Transferability of Adversarial Examples

• 2021 ICCV Admix: Enhancing the Transferability of Adversarial Attacks

• 2021 CVPR Simulating Unknown Target Models for Query-Efficient Black-box Attacks

• 2022 CVPR Improving Adversarial Transferability via Neuron Attribution-Based Attacks

• 2022 IJCAI A Few Seconds Can Change Everything: Fast Decision-based Attacks against DNNs

• 2023 CVPR Improving the Transferability of Adversarial Samples by Path-Augmented Method

• 2023 ICCV Backpropagation Path Search On Adversarial Transferability

• 2023 CVPR Minimizing Maximum Model Discrepancy for Transferable Black-box Targeted Attacks

• 2023 ICLR Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples

• 2023 CVPR Towards Transferable Targeted Adversarial Examples

• 2023 CVPR Introducing Competition to Boost the Transferability of Targeted Adversarial Examples through Clean Feature Mixup

• 2023 CVPR StyLess: Boosting the Transferability of Adversarial Examples

• 2023 CVPR Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization

• 2015 arxiv Foveation-based Mechanisms Alleviate Adversarial Examples
• 2016 S&P Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
• 2017 ICCV Adversarial Examples for Semantic Segmentation and Object Detection
• 2017 arxiv DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples
• 2017 arxiv Generative Adversarial Trainer: Defense to Adversarial Perturbations with GAN
• 2018 AAAI Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradients
• 2019 NuerIPS Adversarial Examples are not Bugs, they are Features
• 2019 ICML Theoretically Principled Trade-off between Robustness and Accuracy
• 2020 NeurIPS Adversarial Self-Supervised Contrastive Learning
• 2020 ICML Adversarial Neural Pruning with Latent Vulnerability Suppression
• 2020 ICLR Improving adversarial robustness requires revisiting misclassified examples
• 2020 ICML Learning Adversarially Robust Representations via Worst-Case Mutual Information Maximization
• 2021 arxiv Meta Adversarial Training against Universal Patches
• 2020 CVPR Adversarial Robustness- From Self-Supervised Pre-Training to Fine-Tuning
• 2021 ICCV Adversarial Attacks are Reversible with Natural Supervision
• 2021 ICLR Self-supervised adversarial robustness for the low-label, high-data regime
• 2021 NeurIPS When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?
• 2022 USENIX Transferring Adversarial Robustness Through Robust Representation Matching
• 2022 ICML Improving Adversarial Robustness via Mutual Information Estimation

• 2017 ICLRWorkshop Early Methods for Detecting Adversarial Images
• 2017 ICLR On Detecting Adversarial Perturbations
• 2017 Arixv Detecting Adversarial Samples from Artifacts
• 2017 ICCV SafetyNet: Detecting and Rejecting Adversarial Examples Robustly
• 2017 CCS MagNet: a Two-Pronged Defense against Adversarial Examples
• 2018 ICLR Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionality
• 2018 arxiv Detecting Adversarial Perturbations with Saliency
• 2018 NDSS Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks
• 2019 NDSS NIC: Detecting Adversarial Samples with Neural Network Invariant Checking
• 2019 arxiv Model-based Saliency for the Detection of Adversarial Examples
• 2020 ICJNN Detection of Adversarial Examples in Deep Neural Networks with Natural Scene Statistics
• 2020 arxiv Detection Defense Against Adversarial Attacks with Saliency Map
• 2020 arxiv RAID: Randomized Adversarial-Input Detection for Neural Networks
• 2020 AAAI ML-LOO: Detecting Adversarial Examples with Feature Attribution
• 2021 Springer Adversarial example detection based on saliency map features
• 2020 KDD Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defense
• 2020 SPAI Stateful Detection of Black-Box Adversarial Attacks
• 2021 arxiv ExAD: An Ensemble Approach for Explanation-based Adversarial Detection
• 2021 AAAI Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain
• 2021 ICML Workshop Detecting AutoAttack Perturbations in the Frequency Domain
• 2021 IJCNN SpectralDefense: Detecting Adversarial Attacks on CNNs in the Fourier Domain
• 2021 MM Workshop Frequency Centric Defense Mechanisms against Adversarial Examples
• 2022 USENIX Blacklight: Scalable Defense for Neural Networks against Query-Based Black-Box Attacks
• 2022 From Spatial to Spectral Domain, a New Perspective for Detecting Adversarial Examples

• 2016 CVPR A study of the effect of JPG compression on adversarial images
• 2017 arxiv Mitigating adversarial effects through randomization
• 2018 CVPR Defense against Universal Adversarial Perturbations
• 2018 CVPR Deflecting Adversarial Attacks with Pixel Deflection
• 2018 CVPR Defense against Adversarial Attacks Using High-Level Representation Guided Denoiser
• 2019 ICCV CIIDefence: Defeating Adversarial Attacks by Fusing Class-specific Image Inpainting and Image Denoising
• 2020 CVPR A Self-supervised Approach for Adversarial Robustness
• 2021 ICCV Removing Adversarial Noise in Class Activation Feature Space
• 2021 ICML Towards Defending against Adversarial Examples via Attack-Invariant Features
• 2022 CVPR Workshop SymDNN- Simple & Effective Adversarial Robustness for Embedded Systems
• 2022 ICLR Reverse Engineering of Imperceptible Adversarial Image Perturbations
• 2022 ICML Modeling Adversarial Noise for Adversarial Training

• 2018 NDSS TextBugger: Generating Adversarial Text Against Real-world Applications
• 2018 ACL HotFlip: White-Box Adversarial Examples for Text Classification
• 2019 S&P Intriguing Properties of Adversarial ML Attacks in the Problem Space
• 2019 IJCNN Adversarial Attacks on Deep Neural Networks for Time Series Classification
• 2020 AAAI Is BERT Really Robust? A Strong Baseline for Natural Language Attack on Text Classification and Entailment

• 2019 ICML Certified Adversarial Robustness via Randomized Smoothing
• 2019 NeurIPS Certified Adversarial Robustness with Additive Noise
• 2020 NIPS Denoised Smoothing: A Provable Defense for Pretrained Classifiers
• 2022 ICLR How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective
• 2022 ICLR On the Certified Robustness for Ensemble Models and Beyond
• 2022 ICML Intriguing Properties of Input-Dependent Randomized Smoothing
• 2023 ICLR (Certified!!) Adversarial Robustness for Free!
• 2023 ICLR DensePure: Understanding Diffusion Models towards Adversarial Robustness

• 2012 TROJANZOO: Everything you ever wanted to know about neural backdoors (but were afraid to ask)
• 2020 Backdoor Learning: A Survey

• 2017 Arxiv BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain
• 2018 NDSS Trojaning Attack on Neural Networks
• 2018 CCS Model-Reuse Attacks on Deep Learning Systems
• 2019 CCS Latent Backdoor Attacks on Deep Neural Networks
• 2020 CCS A Tale of Evil Twins: Adversarial Inputs versus Poisoned Models
• 2020 AAAI Hidden Trigger Backdoor Attacks
• 2020 NeurIPS Input-Aware Dynamic Backdoor Attack
• 2020 arxiv Dynamic Backdoor Attacks Against Machine Learning Models
• 2020 arxiv Backdoor Attacks on the DNN Interpretation System
• 2021 USENIX Security Blind Backdoors in Deep Learning Models
• 2021 ICCV Invisible Backdoor Attack with Sample-Specific Triggers
• 2021 Infocom Invisible Poison: A Blackbox Clean Label Backdoor Attack to Deep Neural Networks
• 2021 ICLR WaNet -- Imperceptible Warping-based Backdoor Attack
• 2022 IJCAI Data-Efficient Backdoor Attacks
• 2022 AAAI Hibernated Backdoor- A Mutual Information Empowered Backdoor Attack to Deep Neural Networks
• 2022 CVPR Backdoor Attacks on Self-Supervised Learning
• 2022 CVPR BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning
• 2022 ICML Neurotoxin: Durable Backdoors in Federated Learning
• 2023 Infocom Mind Your Heart: Stealthy Backdoor Attack on Dynamic Deep Neural Network in Edge Computing

• 2018 Arxiv Backdooring Convolutional Neural Networks via Targeted Weight Perturbations
• 2020 arxiv Don't Trigger Me! A Triggerless Backdoor Attack Against Deep Neural Networks
• 2020 CVPR TBT: Targeted Neural Network Attack with Bit Trojan
• 2020 CIKM Can Adversarial Weight Perturbations Inject Neural Backdoors?
• 2020 SIGKDD An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networks
• 2021 ICSE DeepPayload: Black-box Backdoor Attack on Deep Learning Models through Neural Payload Injection
• 2021 ICLR WORKSHOP Subnet Replacement: Deployment-stage backdoor attack against deep neural networks in gray-box setting

• 2020 PMLR How To Backdoor Federated Learning

• 2018 RAID Fine-Pruning: Defending Against Backdooring Attacks on Deep Neural Networks
• 2018 NuerIPS Spectral Signatures in Backdoor Attacks
• 2019 S&P Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks
• 2019 CCS ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation
• 2019 IJCAI DeepInspect: A Black-box Trojan Detection and Mitigation Framework for Deep Neural Networks
• 2019 AAAI Detecting Backdoor Attacks on Deep Neural Networks by Activation Clustering
• 2019 ACSAC STRIP: A Defence Against Trojan Attacks on Deep Neural Networks
• 2020 ECCV One-pixel Signature: Characterizing CNN Models for Backdoor Detection
• 2020 ICDM TABOR: A Highly Accurate Approach to Inspecting and Restoring Trojan Backdoors in AI Systems
• 2020 ACSAC Februus: Input Purification Defense Against Trojan Attacks on Deep Neural Network
• 2021 ICLR Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
• 2021 NeurIPS Anti-Backdoor Learning: Training Clean Models on Poisoned Data
• 2021 NeurIPS Adversarial Neuron Pruning Purifies Backdoored Deep Models
• 2022 USENIX Poison Forensics: Traceback of Data Poisoning Attacks in Neural Networks

• 2017 ICML Understanding Black-box Predictions via Influence Functions
• 2018 NeurIPS Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks
• 2021 NeurIPS Manipulating SGD with Data Ordering Attacks
• 2022 AAAI CLPA: Clean-Label Poisoning Availability Attacks Using Generative Adversarial Nets
• 2022 USENIX PoisonedEncoder-Poisoning the Unlabeled Pre-training Data in Contrastive Learning

• 2014 ISCA Flipping Bits in Memory Without Accessing Them: An Experimental Study of DRAM Disturbance Errors

• 2019 USENIX Terminal brain damage: Exposing the graceless degradation in deep neural networks under hardware fault attacks
• 2020 USENIX DeepHammer: Depleting the Intelligence of Deep Neural Networks through Targeted Chain of Bit Flips

• 2021 Arxiv Survey- Leakage and Privacy at Inference Time

• 2015 CCS Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
• 2017 CCS Deep Models Under the GAN: Information Leakage from Collaborative Deep Learning
• 2019 NeurIPS Deep Leakage from Gradients
• 2020 Arxiv iDLG: Improved Deep Leakage from Gradients
• 2020 USENIX Security Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning
• 2020 CVPR Dreaming to Distill: Data-free Knowledge Transfer via DeepInversion
• 2021 CVPR See through Gradients: Image Batch Recovery via GradInversion
• 2021 计算机研究与发展 通用深度学习语言模型的隐私风险评估
• 2022 USENIX Security Theory-Oriented Deep Leakage from Gradients via Linear Equation Solver
• 2022 Arxiv Reconstructing Training Data from Trained Neural Networks
• 2022 ICLR Label Leakage and Protection in Two-party Split Learning
• 2022 ICLR Robbing the Fed: Directly Obtaining Private Data in Federated Learning with Modified Models

• 2017 S&P Membership Inference Attacks against Machine Learning Models
• 2018 Arxiv Understanding Membership Inferences on Well-Generalized Learning Models
• 2018 CSF Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting
• 2018 CCS Machine Learning with Membership Privacy using Adversarial Regularization
• 2019 NDSS ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models
• 2019 CCS Privacy Risks of Securing Machine Learning Models against Adversarial Examples
• 2019 CCS MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples
• 2019 S&P Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
• 2019 NIPSWorkshop Sampling Attacks: Amplification of Membership Inference Attacks by Repeated Queries
• 2019 ICML White-box vs Black-box: Bayes Optimal Strategies for Membership Inference
• 2020 USENIX Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inference
• 2021 CCS When Machine Unlearning Jeopardizes Privacy
• 2021 ICML Label-Only Membership Inference Attacks
• 2021 ICCV Membership Inference Attacks are Easier on Difficult Problems
• 2021 ICML When Does Data Augmentation Help With Membership Inference Attacks?
• 2021 CCS Membership Leakage in Label-Only Exposures
• 2021 AAAI Membership Privacy for Machine Learning Models Through Knowledge Transfer
• 2021 USENIX Systematic Evaluation of Privacy Risks of Machine Learning Models
• 2021 Arxiv Source Inference Attacks in Federated Learning
• 2021 CVPR On the Difficulty of Membership Inference Attacks
• 2021 AIES On the Privacy Risks of Model Explanations
• 2021 AsiaCCS Membership Feature Disentanglement Network
• 2022 Arxiv Truth Serum: Poisoning Machine Learning Models to Reveal Their Secrets
• 2022 ECCV Semi-Leak- Membership Inference Attacks Against Semi-supervised Learning
• 2022 TDSC Membership Inference Attacks against Machine Learning Models via Prediction Sensitivity
• 2022 USENIX Membership Inference Attacks and Defenses in Neural Network Pruning
• 2022 S&P Membership Inference Attacks From First Principles
• 2022 NeurlPS M4I: Multi-modal Models Membership Inference

• 2018 CCS Property Inference Attacks on Fully Connected Neural Networksusing Permutation Invariant Representations

• 2017 CCS Machine Learning Models that Remember Too Much
• 2022 ICML On the Difficulty of Defending Self-Supervised Learning against Model Extraction

• 2019 NAACL On Measuring Social Biases in Sentence Encoders
• 2020 AAAI On Measuring and Mitigating Biased Inferences of Word Embeddings
• 2020 EMNLP CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Models
• 2020 ACL Towards Debiasing Sentence Representations
• 2021 ACL StereoSet: Measuring stereotypical bias in pretrained language models
• 2021 ACL Probing Toxic Content in Large Pre-Trained Language Models
• 2021 ICML Towards Understanding and Mitigating Social Biases in Language Models
• 2021 TransACL Self-Diagnosis and Self-Debiasing:A Proposal for Reducing Corpus-Based Bias in NLP
• 2021 EACL Debiasing Pre-trained Contextualised Embeddings
• 2021 EMNLP Sustainable Modular Debiasing of Language Models
• 2021 EMNLP Mitigating Language-Dependent Ethnic Bias in BERT
• 2021 ICLR FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders
• 2022 ACL Auto-Debias: Debiasing Masked Language Models with Automated Biased Prompts
• 2022 ACL An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models
• 2022 EMNLP MABEL: Attenuating Gender Bias using Textual Entailment Data
• 2022 EMNLP Debiasing Pretrained Text Encoders by Paying Attention to Paying Attention

• 2019 AsiaCCS IPGuard: Protecting Intellectual Property of Deep Neural Networks via Fingerprinting the Classification Boundary
• 2019 CVPR Sensitive-Sample Fingerprinting of Deep Neural Networks
• 2020 Computer Communications AFA: Adversarial fingerprinting authentication for deep neural networks
• 2020 ACSAC Secure and Verifiable Inference in Deep Neural Networks
• 2021 ESORICS TAFA: A Task-Agnostic Fingerprinting Algorithm for Neural Networks
• 2021 ICLR Deep Neural Network Fingerprinting by Conferrable Adversarial Examples
• 2021 ISCAS Fingerprinting Deep Neural Networks - a DeepFool Approach
• 2021 ISSTA ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection
• 2021 BMVC Intrinsic Examples: Robust Fingerprinting of Deep Neural Networks
• 2021 IJCAI Characteristic Examples: High-Robustness, Low-Transferability Fingerprinting of Neural Networks
• 2021 Journal of Computer Research and Development An Evasion Algorithm to Fool Fingerprint Detector for Deep Neural Networks
• 2022 KDD MetaV: A Meta-Verifier Approach to Task-Agnostic Model Fingerprinting
• 2022 S&P Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models
• 2022 USENIX Teacher Model Fingerprinting Attacks Against Transfer Learning
• 2022 CVPR Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations
• 2022 IJCAI MetaFinger: Fingerprinting the Deep Neural Networks with Meta-training
• 2022 ICIP Neural network fragile watermarking with no model performance degradation
• 2022 TIFS A DNN Fingerprint for Non-Repudiable Model Ownership Identification and Piracy Detection

• 2022 IEEE TIFS Your Model Trains on My Data? Protecting Intellectual Property of Training Data via Membership Fingerprint Authentication

• 2017 ICMR Embedding Watermarks into Deep Neural Networks
• 2018 USENIX Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooring
• 2019 ASPLOS DeepSigns: An End-to-End Watermarking Framework for Ownership Protection of Deep Neural Networks\
• 2019 ICASSP Attacks on Digital Watermarks for Deep Neural Networks
• 2020 AsiaCCS Robust Membership Encoding: Inference Attacks and Copyright Protection for Deep Learning
• 2021 USENIX Entangled Watermarks as a Defense against Model Extraction
• 2021 WWW RIGA: Covert and Robust White-BoxWatermarking of Deep Neural Networks
• 2021 KSEM Fragile Neural Network Watermarking with Trigger Image Set
• 2022 arxiv AWEncoder: Adversarial Watermarking Pre-trained Encoders in Contrastive Learning
• 2022 AAAI DeepAuth: A DNN Authentication Framework by Model-Unique and Fragile Signature Embedding
• 2022 Oakland S&P SoK- How Robust is Image Classification Deep Neural Network Watermarking?
• 2022 Oakland S&P Copy, Right? A Testing Framework for Copyright Protection of Deep Learning Models
• 2023 Arxiv The Stable Signature: Rooting Watermarks in Latent Diffusion Model

• 2020 NeurIPS Workshop Open-sourced Dataset Protection via Backdoor Watermarking
• 2020 ICML Radioactive data: tracing through training

• 2019 NeurIPS Making AI Forget You: Data Deletion in Machine Learning
• 2020 MICCAI Have you forgotten? A method to Assess If Machine Learning Models Have Forgotten Data
• 2020 CVPR Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks
• 2021 ECCV Forgetting Outside the Box- Scrubbing Deep Networks of Information Accessible from Input-Output Observations
• 2021 S&P Oakland Machine Unlearning
• 2021 AAAI Amnesiac Machine Learning
• 2021 MICCAI EMA: Auditing Data Removal from Trained Model
• 2021 ICML Certified Data Removal from Machine Learning Models
• 2022 TDSC Learn to Forget: Machine Unlearning via Neuron Masking
• 2022 AAAI PUMA: Performance Unchanged Model Augmentation for Training Data Removal
• 2022 AAAI Hard to Forget: Poisoning Attacks on Certified Machine Unlearning
• 2022 Arxiv A Survey of Machine Unlearning
• 2022 Arxiv Zero-shot machine unlearning
• 2022 ECCV Learning with Recoverable Forgetting
• 2022 USENIX On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning

• 2014 MIPS On the Number of Linear Regions of Deep Neural Networks
• 2020 PNAS Overparameterized neural networks implement associative memory

• 2019 NIPS Superposition of many models into one
• 2020 ICLR Once-for-All: Train One Network and Specialize it for Efficient Deployment
• 2020 arxiv On Hiding Neural Networks Inside Neural Networks
• 2021 arxiv Recurrent Parameter Generators

• 2021 AAAI TransTailor- Pruning the Pre-trained Model for Improved Transfer Learning
• 2021 NIPS Supervised Contrastive Learning

• 2017 ICLR Loss-aware Binarization of Deep Networks
• 2018 NIPS Scalable Methods for 8-bit Training of Neural Networks
• 2018 CVPR Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference
• 2018 Google White Paper Quantizing deep convolutional networks for efficient inference: A whitepaper
• 2018 ICLR Loss-aware Weight Quantization of Deep Networks

• 2017 CVPR Spatially Adaptive Computation Time for Residual Networks
• 2018 ICLR Multi-Scale Dense Networks for Resource Efficient Image Classification
• 2018 ECCV SkipNet: Learning Dynamic Routing in Convolutional Networks
• 2019 ICML Shallow-Deep Networks: Understanding and Mitigating Network Overthinking
• 2020 NeurIPS BERT Loses Patience: Fast and Robust Inference with Early Exit
• 2020 ICML PoWER-BERT: Accelerating BERT Inference via Progressive Word-vector Elimination
• 2021 PAMI Dynamic Neural Networks: A Survey
• 2021 IEEE TETC Fully Dynamic Inference with Deep Neural Networks
• 2022 AAAI ReX: an Efficient Approach to Reducing Memory Cost in Image Classification
• 2022 KDD Learned Token Pruning for Transformers
• 2022 ACL Transkimmer: Transformer Learns to Layer-wise Skim
• 2023 EACL A Survey on Dynamic Neural Networks for Natural Language Processing

• 2020 ICLR Triple Wins: Boosting Accuracy, Robustness and Efficiency Together by Enabling Input-Adaptive Inference
• 2020 CVPR ILFO: Adversarial Attack on Adaptive Neural Networks
• 2021 ICLR A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference
• 2021 IEEE IOTJ DefQ: Defensive Quantization against Inference Slow-down Attack for Edge Computing
• 2021 Arxiv Fingerprinting Multi-exit Deep Neural Network Models via Inference Time
• 2022 CCS Auditing Membership Leakages of Multi-Exit Networks
• 2022 ICSE EREBA: Black-box Energy Testing of Adaptive Neural Networks
• 2022 FSE NMTSloth: Understanding and Testing Efficiency Degradation of Neural Machine Translation Systems
• 2022 CVPR NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models

• 2014 ECCV Visualizing and Understanding Convolutional Networks
• 2014 ICLR Workshop Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps
• 2016 CVPR Learning Deep Features for Discriminative Localization
• 2017 ICCV Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization
• 2018 BMVC RISE: Randomized Input Sampling for Explanation of Black-box Models
• 2019 NeurIPS Full-Gradient Representation for Neural Network Visualization
• 2020 IJCNN Black-Box Saliency Map Generation Using Bayesian Optimisation
• 2021 CVPR Black-box Explanation of Object Detectors via Saliency Maps
• 2021 Arxiv Where do Models go Wrong? Parameter-Space Saliency Maps for Explainability
• 2022 ECCV SESS：Saliency Enhancing with Scaling and Sliding
• 2022 AAAI Interpretable Generative Adversarial Networks

• 2017 Arxiv The (Un)reliability of saliency methods
• 2018 NeurlPS Sanity Checks for Saliency Maps
• 2019 NeurlPS On the (In)fidelity and Sensitivity for Explanations
• 2022 ICLR Workshop Saliency Maps Contain Network "Fingerprints"

• 2019 AAAI Interpretation of Neural Networks Is Fragile
• 2019 ICCV Fooling Network Interpretation in Image Classification
• 2019 NeurlPS Fooling Neural Network Interpretations via Adversarial Model Manipulation
• 2019 NeurlPS Explanations can be manipulated and geometry is to blame
• 2020 USENIX Interpretable Deep Learning under Fire

• 2020 arxiv A simple defense against adversarial attacks on heatmap explanations
• 2022 arxiv Defense Against Explanation Manipulation

• 2018 arxiv Anomaly Detection for Skin Disease Images Using Variational Autoencoder

• 2017 NeurIPS Attention Is All You Need

• 2018 ICML Image Transformer
• 2020 ECCV End-to-End Object Detection with Transformers
• 2020 ICLR An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• 2021 Arxiv TransReID: Transformer-based Object Re-Identification

• 2015 Nature Human-level control through deep reinforcement learning

• 2016 ICML Asynchronous Methods for Deep Reinforcement Learning

• 2017 ICLR Workshop Adversarial Attacks on Neural Network Policies
• 2017 MLDM Vulnerability of Deep Reinforcement Learning toPolicy Induction Attacks
• 2017 IJCAI Tactics of Adversarial Attack on Deep Reinforcement Learning Agents
• 2018 CSCS Sequential Attacks on Agents for Long-Term Adversarial Goals
• 2020 S&P Workshop On the Robustness of Cooperative Multi-Agent Reinforcement Learning
• 2020 ICML Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning

• 2017 ICML Robust Adversarial Reinforcement Learning

• 2020 arxiv Deep Learning for Person Re-identification: A Survey and Outlook

• 2020 arxiv FastReID: A Pytorch Toolbox for General Instance Re-identification

• 2019 CVPR workshop Bag of Tricks and A Strong Baseline for Deep Person Re-identification
• 2015 ICCV Scalable Person Re-identification: A Benchmark
• 2016 ECCV workshop Performance Measures and a Data Set for Multi-Target, Multi-Camera Tracking
• 2016 arxiv PersonNet: Person Re-identification with Deep Convolutional Neural Networks

• 2018 ECCV Adversarial Open-World Person Re-Identification
• 2019 PAMI Adversarial Metric Attack and Defense for Person Re-identification
• 2019 ICCV advPattern: Physical-World Attacks on Deep Person Re-Identification via Adversarially Transformable Patterns
• 2020 CVPR Transferable, Controllable, and Inconspicuous Adversarial Attacks on Person Re-identification With Deep Mis-Ranking
• 2020 IEEE ACCESS An Effective Adversarial Attack on Person Re-Identification in Video Surveillance via Dispersion Reduction
• 2020 ECCV Adversarial T-shirt! Evading Person Detectors in A Physical World

• 2021 Arxiv SoK: Anti-Facial Recognition Technology

• 2016 CCS Accessorize to a Crime: Real and Stealthy Attacks on State-of-the-Art Face Recognition
• 2019 ISVC DeepPrivacy: A Generative Adversarial Network for Face Anonymization
• 2019 CVPR Efficient Decision-based Black-box Adversarial Attacks on Face Recognition
• 2019 IMWUT VLA: A Practical Visible Light-based Attack on Face Recognition Systems in Physical World
• 2020 CVPR Workshop Adversarial Light Projection Attacks on Face Recognition Systems: A Feasibility Study
• 2020 USENIX Fawkes: Protecting Privacy against Unauthorized Deep Learning Models
• 2021 ICCV Towards Face Encryption by Generating Adversarial Identity Masks
• 2021 ICLR LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition
• 2021 ICLR Unlearnable Examples: Making Personal Data Unexploitable

• 1999 SIGIR Probabilistic Latent Semantic Indexing
• 2007 NeurIPSProbabilistic Matrix Factorization
• 2017 AAAISeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
• 2017 ICML Toward Controlled Generation of Text

• 2014 Convex Optimization: Algorithms and Complexity
• 2019 AAAI AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks

• Optimization Algorithms on Matrix Manifolds

• 2014 NeurIPS Learning, Regularization and Ill-Posed Inverse Problems
• 2015 ICML Workshop Norm-Based Capacity Control in Neural Networks

• 2020 CVPR Counterfactual Samples Synthesizing for Robust Visual Question Answering
• 2020 CVPR Towards Causal VQA: Revealing and Reducing Spurious Correlations by Invariant and Covariant Semantic Editing
• 2020 CVPR Visual Commonsense R-CNN
• 2021 CVPR Counterfactual VQA: A Cause-Effect Look at Language Bias
• 2020 NeurIPS Investigating Gender Bias in Language Models Using Causal Mediation Analysis
• 2021 NeurIPS A Causal Lens for Controllable Text Generation
• 2022 ACL Can Prompt Probe Pretrained Language Models? Understanding the Invisible Risks from a Causal View
• 2022 EMNLP Mitigating Spurious Correlation in Natural Language Understanding with Counterfactual Inference

• Blind Signal Separation Blind signal separation: statistical principles
• 2018 ICML MINE: Mutual Information Neural Estimation
• 2019 ICLR Learning deep representations by mutual information estimation and maximization