conftrace_

vulnerabilities

4 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (2) red teaming (2) problematic prompts (1) exploit (1) sandbox (1) tamper-resistant models (1) jailbreak (1) llms (1) malicious actor (1) real-world condition (1)

Papers

Automated Red Teaming with GOAT: the Generative Offensive Agent Tester ICML 2025 CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities ICML 2025 Position: Editing Large Language Models Poses Serious Safety Risks ICML 2025 Prompting4Debugging: Red-Teaming Text-to-Image Diffusion Models by Finding Problematic Prompts ICML 2024