conftrace_

defenses

3 papers

Explore in graph

Co-occurring keywords · papers mentioning both

adversarial attack (2) iqa metrics (1) no-reference iqa metrics (1) masking function (1) trajectory re-execution (1) wolfpack (1) collaboration (1) benchmark (1) large language model (1) indirect prompt injection (1)

Papers

Guardians of Image Quality: Benchmarking Defenses Against Adversarial Attacks on Image Quality Metrics ICML 2025 MELON: Provable Defense Against Indirect Prompt Injection Attacks in AI Agents ICML 2025 Wolfpack Adversarial Attack for Robust Multi-Agent Reinforcement Learning ICML 2025