no code implementations • 6 May 2024 • Shang Shang, Xinqiang Zhao, Zhongjiang Yao, Yepeng Yao, Liya Su, Zijing Fan, Xiaodan Zhang, Zhengwei Jiang
To demonstrate and address the underlying maliciousness, we propose a theoretical hypothesis and analytical approach, and introduce a new black-box jailbreak attack methodology named IntentObfuscator, exploiting this identified flaw by obfuscating the true intentions behind user prompts. This approach compels LLMs to inadvertently generate restricted content, bypassing their built-in content security measures.
no code implementations • 24 Oct 2023 • Xiaoyi Chen, Siyuan Tang, Rui Zhu, Shijun Yan, Lei Jin, ZiHao Wang, Liya Su, XiaoFeng Wang, Haixu Tang
In the attack, one can construct a PII association task, whereby an LLM is fine-tuned using a minuscule PII dataset, to potentially reinstate and reveal concealed PIIs.