4 papers
TASO: Jailbreak LLMs via Alternative Template and Suffix Optimization
Yanting Wang, Runpeng Geng, Jinghui Chen +2
Many recent studies showed that LLMs are vulnerable to jailbreak attacks, where an attacker can perturb the input of an LLM to induce it to generate an output for a harmful questio…
PISanitizer: Preventing Prompt Injection to Long-Context LLMs via Prompt Sanitization
Runpeng Geng, Yanting Wang, Chenlong Yin +3
Long context LLMs are vulnerable to prompt injection, where an attacker can inject an instruction in a long context to induce an LLM to generate an attacker-desired output. Existin…
Optimizing Token Choice for Code Watermarking: An RL Approach
Zhimeng Guo, Huaisheng Zhu, Siyuan Xu +3
Protecting intellectual property on LLM-generated code necessitates effective watermarking systems that can operate within code's highly structured, syntactically constrained natur…
Dataset Distillation via Adversarial Prediction Matching
Mingyang Chen, Bo Huang, Junda Lu +4
Dataset distillation is the technique of synthesizing smaller condensed datasets from large original datasets while retaining necessary information to persist the effect. In this p…