Richard Fang

13 papers A* 2Journal 8Unranked 3
YearRankTypeTitle / Venue / Authors
2026 — conf
Teams of LLM Agents can Exploit Zero-Day Vulnerabilities.
EACL (Volume 1: Long Papers)
Yuxuan Zhu, Antony Kellermann, Akul Gupta, Philip Li, Richard Fang, Rohan Bindu, Daniel Kang
2025 — conf
Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents.
NAACL (Findings)
Qiusi Zhan, Richard Fang, Henil Shalin Panchal, Daniel Kang
2025 J jnl
Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents.
CoRR
Qiusi Zhan, Richard Fang, Henil Shalin Panchal, Daniel Kang
2025 A* conf
CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities.
ICML
Yuxuan Zhu, Antony Kellermann, Dylan Bowman, Philip Li, Akul Gupta, Adarsh Danda, Richard Fang, Conner Jensen, Eric Ihli, Jason Benn, Jet Geronimo, Avi Dhir, Sudhit Rao, Kaicheng Yu, Twm Stone, Daniel Kang
2025 J jnl
CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities.
CoRR
Yuxuan Zhu, Antony Kellermann, Dylan Bowman, Philip Li, Akul Gupta, Adarsh Danda, Richard Fang, Conner Jensen, Eric Ihli, Jason Benn, Jet Geronimo, Avi Dhir, Sudhit Rao, Kaicheng Yu, Twm Stone, Daniel Kang
2024 J jnl
LLM Agents can Autonomously Exploit One-day Vulnerabilities.
CoRR
Richard Fang, Rohan Bindu, Akul Gupta, Daniel Kang
2024 J jnl
LLM Agents can Autonomously Hack Websites.
CoRR
Richard Fang, Rohan Bindu, Akul Gupta, Qiusi Zhan, Daniel Kang
2024 — conf
Removing RLHF Protections in GPT-4 via Fine-Tuning.
NAACL (Short Papers)
Qiusi Zhan, Richard Fang, Rohan Bindu, Akul Gupta, Tatsunori Hashimoto, Daniel Kang
2024 J jnl
Teams of LLM Agents can Exploit Zero-Day Vulnerabilities.
CoRR
Richard Fang, Rohan Bindu, Akul Gupta, Qiusi Zhan, Daniel Kang
2024 A* conf
VGX: Large-Scale Sample Generation for Boosting Learning-Based Software Vulnerability Analyses.
ICSE
Yu Nong, Richard Fang, Guangbei Yi, Kunsong Zhao, Xiapu Luo, Feng Chen, Haipeng Cai
2024 J jnl
Voice-Enabled AI Agents can Perform Common Scams.
CoRR
Richard Fang, Dylan Bowman, Daniel Kang
2023 J jnl
Removing RLHF Protections in GPT-4 via Fine-Tuning.
CoRR
Qiusi Zhan, Richard Fang, Rohan Bindu, Akul Gupta, Tatsunori Hashimoto, Daniel Kang
2023 J jnl
VGX: Large-Scale Sample Generation for Boosting Learning-Based Software Vulnerability Analyses.
CoRR
Yu Nong, Richard Fang, Guangbei Yi, Kunsong Zhao, Xiapu Luo, Feng Chen, Haipeng Cai