11 papers
CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning
Rahul Markasserithodi, Aditya Joshi, Yuekang Li +3
Despite advances in safety alignment, prompt-rewriting attacks such as persona modulation, fictional framing and persuasion-based reformulation, can bypass safety filters even on f…
Intent2Tx: Benchmarking LLMs for Translating Natural Language Intents into Ethereum Transactions
Zhuoran Pan, Yue Li, Zhi Guan +2
The emergence of Large Language Models (LLMs) offers a transformative interface for Web3, yet existing benchmarks fail to capture the complexity of translating high-level user inte…
Membership Inference Attacks Against Video Large Language Models
Wei Song, Yuxin Cao, Ziqi Ding +3
Video large language models (VideoLLMs) are increasingly trained or instruction-tuned on large-scale video--text corpora collected from heterogeneous sources, raising an immediate…
NGCaptcha: A CAPTCHA Bridging the Past and the Future
Ziqi Ding, Shangzhi Xu, Wei Song +1
CAPTCHAs are widely employed for distinguishing humans from automated bots online. However, current vision based CAPTCHAs face escalating security risks: traditional attacks contin…
Socrates or Smartypants: Testing Logic Reasoning Capabilities of Large Language Models with Logic Programming-based Test Oracles
Zihao Xu, Junchen Ding, Yiling Lou +3
Large Language Models (LLMs) have achieved significant progress in language understanding and reasoning. Evaluating and analyzing their logical reasoning abilities has therefore be…
Laugh, Relate, Engage: Stylized Comment Generation for Short Videos
Xuan Ouyang, Senan Wang, Bouzhou Wang +3
Short-video platforms have become a central medium in the modern Internet landscape, where efficient information delivery and strong interactivity are reshaping user engagement and…