Richard Fang
4 papers · 2024–2026 · 3 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Top co-authors
Research topics
Keywords
llm agent
(3)
model safety
(1)
planning agent
(1)
prompt injection
(1)
adaptive attack
(1)
external tool
(1)
indirect prompt injection
(1)
security defense
(1)
large language model
(1)
web application
(1)
multi-agent system
(1)
real-world condition
(1)
harmful output
(1)
zero-day vulnerability
(1)
vulnerabilities
(1)
exploit
(1)
reinforcement learning
(1)
sandbox
(1)
Papers
Teams of LLM Agents can Exploit Zero-Day Vulnerabilities
EACL 2026
Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
NAACL 2025
CVE-Bench: A Benchmark for AI Agents’ Ability to Exploit Real-World Web Application Vulnerabilities
ICML 2025
Removing RLHF Protections in GPT-4 via Fine-Tuning
NAACL 2024