Skip to content
conftrace_

adversarial defense

356 papers

Explore in graph

Co-occurring keywords · papers mentioning both

adversarial attack (104) adversarial robustness (65) backdoor attack (39) adversarial training (36) adversarial example (28) large language model (28) adversarial learning (28) text classification (26) model robustness (24) neural network (23)

Papers

Refuse Whenever You Feel Unsafe: Improving Safety in LLMs via Decoupled Refusal Training ACL 2025 Robustness Inspired Graph Backdoor Defense ICLR 2025 SafeKey: Amplifying Aha-Moment Insights for Safety Reasoning EMNLP 2025 SafeQuant: LLM Safety Analysis via Quantized Gradient Inspection NAACL 2025 Sanitizing Backdoored Graph Neural Networks: A Multidimensional Approach IJCAI 2025 SDD: Self-Degraded Defense against Malicious Fine-tuning ACL 2025 Seeing Through Deepfakes: A Human-Inspired Framework for Multi-Face Detection ICCV 2025 SINCon: Mitigate LLM-Generated Malicious Message Injection Attack for Rumor Detection ACL 2025 SPIRIT: Patching Speech Language Models against Jailbreak Attacks EMNLP 2025 Split Adaptation for Pre-trained Vision Transformers CVPR 2025 Test-Time Backdoor Detection for Object Detection Models CVPR 2025 Token Highlighter: Inspecting and Mitigating Jailbreak Prompts for Large Language Models AAAI 2025 Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks COLING 2025 Towards Understanding the Robustness of Diffusion-Based Purification: A Stochastic Perspective ICLR 2025 TrojanDec: Data-free Detection of Trojan Inputs in Self-supervised Learning AAAI 2025 TrojanWave: Exploiting Prompt Learning for Stealthy Backdoor Attacks on Large Audio-Language Models EMNLP 2025 Two Sides of the Same Coin: Learning the Backdoor to Remove the Backdoor AAAI 2025 Unraveling the Mystery: Defending Against Jailbreak Attacks Via Unearthing Real Intention COLING 2025 When and Where do Data Poisons Attack Textual Inversion? ICCV 2025 When Witnesses Defend: A Witness Graph Topological Layer for Adversarial Graph Learning AAAI 2025 Why Not Act on What You Know? Unleashing Safety Potential of LLMs via Self-Aware Guard Enhancement ACL 2025 X-Guard: Multilingual Guard Agent for Content Moderation ACL 2025 Zero-Shot Defense Against Toxic Images via Inherent Multimodal Alignment in LVLMs EMNLP 2025 A Closer Look at Robustness of Vision Transformers to Backdoor Attacks WACV 2024 Adversarial Feature Map Pruning for Backdoor ICLR 2024