Adversarial Learning

Adversarially Robust Dense-Sparse Tradeoffs via Heavy-Hitters NeurIPS 2024 Adversarial Training Should Be Cast as a Non-Zero-Sum Game ICLR 2024 AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents NeurIPS 2024 AGS: Affordable and Generalizable Substitute Training for Transferable Adversarial Attack AAAI 2024 Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection NeurIPS 2024 An LLM can Fool Itself: A Prompt-Based Adversarial Attack ICLR 2024 Are AI-Generated Text Detectors Robust to Adversarial Perturbations? ACL 2024 Are Watermarks Bugs for Deepfake Detectors? Rethinking Proactive Forensics IJCAI 2024 ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users NeurIPS 2024 ASETF: A Novel Method for Jailbreak Attack on LLMs through Translate Suffix Embeddings EMNLP 2024 Assist Is Just As Important as the Goal: Image Resurfacing To Aid Model's Robust Prediction WACV 2024 ATM: Adversarial Tuning Multi-agent System Makes a Robust Retrieval-Augmented Generator EMNLP 2024 Attacking Transformers with Feature Diversity Adversarial Perturbation AAAI 2024 Attacks against Abstractive Text Summarization Models through Lead Bias and Influence Functions EMNLP 2024 Attack To Defend: Exploiting Adversarial Attacks for Detecting Poisoned Models CVPR 2024 AttEXplore: Attribution for Explanation with model parameters eXploration ICLR 2024 Backdoor Defense via Test-Time Detecting and Repairing CVPR 2024 BadAgent: Inserting and Activating Backdoor Attacks in LLM Agents ACL 2024 BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning CVPR 2024 BadCLIP: Trigger-Aware Prompt Learning for Backdoor Attacks on CLIP CVPR 2024 BadFusion: 2D-Oriented Backdoor Attacks against 3D Object Detection IJCAI 2024 BadRL: Sparse Targeted Backdoor Attack against Reinforcement Learning AAAI 2024 Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs NeurIPS 2024 Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations ICLR 2024 Beware of Road Markings: A New Adversarial Patch Attack to Monocular Depth Estimation NeurIPS 2024