Richard Fang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Richard Fang has a total of 6 co-authors. Here are the top co-authors by number of shared publications:
- Daniel Kang
University of Illinois (UIUC) Urbana USA
3 shared publications - Qiusi Zhan
University of Illinois Urbana-Champaign
3 shared publications - Akul Gupta
University of Illinois Urbana-Champaign
2 shared publications - Rohan Bindu
University of Illinois Urbana-Champaign
2 shared publications - Tatsunori Hashimoto
Stanford University Stanford University Stanford University
2 shared publications Henil Shalin Panchal
1 shared publication
Latest Publications
- Top Cited PapersOpen Access
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 7101-7117
Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
Qiusi Zhan, Richard Fang, Henil Shalin Panchal, Daniel Kang. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- 1 January 2025
- Published by Association for Computational Linguistics (ACL)
- p. 7101-7117
Top Cited PapersOpen AccessAdaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents
Qiusi Zhan, Richard Fang, Henil Shalin Panchal, Daniel Kang. Findings of the Association for Computational Linguistics: NAACL 2025. 2025.
- Open Access
Removing RLHF Protections in GPT-4 via Fine-Tuning
As large language models (LLMs) have increased in their capabilities, so does their potential for dual use. To reduce harmful outputs, produces and vendors of LLMs have used reinforcement learning with human feedback (RLHF). In tandem, LLM vendors have been increasingly enabling fine-tuning of their most powerful models. However, concurrent work has shown that fine-tuning can remove RLHF protections. We may expect that the most powerful models currently available (GPT-4) are less susceptible to fine-tuning attacks. In this work, we show the contrary: fine-tuning allows attackers to remove RLHF protections with as few as 340 examples and a 95% success rate. These training examples can be automatically generated with weaker models. We further show that removing RLHF protections does not decrease usefulness on non-censored outputs, providing evidence that our fine-tuning strategy does not decrease usefulness despite using weaker models to generate training data. Our results show the need for further research on protections on LLMs.
Open AccessRemoving RLHF Protections in GPT-4 via Fine-Tuning
As large language models (LLMs) have increased in their capabilities, so does their potential for dual use. To reduce harmful outputs, produces and vendors of LLMs have used reinforcement learning with human feedback (RLHF). In tandem, LLM vendors have been increasingly enabling fine-tuning of their most powerful models. However, concurrent work has shown that fine-tuning can remove RLHF protections. We may expect that the most powerful models currently available (GPT-4) are less susceptible to fine-tuning attacks. In this work, we show the contrary: fine-tuning allows attackers to remove RLHF protections with as few as 340 examples and a 95% success rate. These training examples can be automatically generated with weaker models. We further show that removing RLHF protections does not decrease usefulness on non-censored outputs, providing evidence that our fine-tuning strategy does not decrease usefulness despite using weaker models to generate training data. Our results show the need for further research on protections on LLMs.
- Top Cited PapersOpen Access
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 681-687
Removing RLHF Protections in GPT-4 via Fine-Tuning
Qiusi Zhan, Richard Fang, Rohan Bindu, Akul Gupta, Tatsunori Hashimoto, Daniel Kang. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers). 2024.
- 1 January 2024
- Published by Association for Computational Linguistics (ACL)
- p. 681-687
Top Cited PapersOpen AccessRemoving RLHF Protections in GPT-4 via Fine-Tuning
Qiusi Zhan, Richard Fang, Rohan Bindu, Akul Gupta, Tatsunori Hashimoto, Daniel Kang. Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers). 2024.