4 papers
Character as a Latent Variable in Large Language Models: A Mechanistic Account of Emergent Misalignment and Conditional Safety Failures
Yanghao Su, Wenbo Zhou, Tianwei Zhang +4
Emergent Misalignment refers to a failure mode in which fine-tuning large language models (LLMs) on narrowly scoped data induces broadly misaligned behavior. Prior explanations mai…
SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
Peigui Qi, Kunsheng Tang, Wenbo Zhou +5
Text-to-image models have shown remarkable capabilities in generating high-quality images from natural language descriptions. However, these models are highly vulnerable to adversa…
BURN: Backdoor Unlearning via Adversarial Boundary Analysis
Yanghao Su, Jie Zhang, Yiming Li +6
Backdoor unlearning aims to remove backdoor-related information while preserving the model's original functionality. However, existing unlearning methods mainly focus on recovering…
Exploiting Vulnerabilities in Speech Translation Systems through Targeted Adversarial Attacks
Chang Liu, Haolin Wu, Xi Yang +7
As speech translation (ST) systems become increasingly prevalent, understanding their vulnerabilities is crucial for ensuring robust and reliable communication. However, limited wo…