Security

Confidential-PROFITT: Confidential PROof of FaIr Training of Trees ICLR 2023 IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI NeurIPS 2023 Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training NeurIPS 2023 Preprocessors Matter! Realistic Decision-Based Attacks on Machine Learning Systems ICML 2023 TextShield: Beyond Successfully Detecting Adversarial Sentences in text classification ICLR 2023 The Dark Side of AutoML: Towards Architectural Backdoor Search ICLR 2023 TrojText: Test-time Invisible Textual Trojan Insertion ICLR 2023 UNICORN: A Unified Backdoor Trigger Inversion Framework ICLR 2023 Adversarial Laser Spot: Robust and Covert Physical-World Attack to DNNs ACML 2022 A Unified Evaluation of Textual Backdoor Learning: Frameworks and Benchmarks NeurIPS 2022 BadPre: Task-agnostic Backdoor Attacks to Pre-trained NLP Foundation Models ICLR 2022 COPA: Certifying Robust Policies for Offline Reinforcement Learning against Poisoning Attacks ICLR 2022 Defending against Model Stealing via Verifying Embedded External Features AAAI 2022 Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation IJCAI 2022 Few-Shot Backdoor Attacks on Visual Object Tracking ICLR 2022 Increasing the Cost of Model Extraction with Calibrated Proof of Work ICLR 2022 On the Importance of Difficulty Calibration in Membership Inference Attacks ICLR 2022 Real-Time Neural Voice Camouflage ICLR 2022 Beyond L_p Clipping: Equalization based Psychoacoustic Attacks against ASRs ACML 2021 Decentralized Attribution of Generative Models ICLR 2021 Deep Neural Network Fingerprinting by Conferrable Adversarial Examples ICLR 2021 Vulnerability-Aware Poisoning Mechanism for Online RL with Unknown Dynamics ICLR 2021 BREAKING CERTIFIED DEFENSES: SEMANTIC ADVERSARIAL EXAMPLES WITH SPOOFED ROBUSTNESS CERTIFICATES ICLR 2020 Thieves on Sesame Street! Model Extraction of BERT-based APIs ICLR 2020 Structured Adversarial Attack: Towards General Implementation and Better Interpretability ICLR 2019