4 accepted papers
Safety-aware shared autonomy aims to enable an autonomous agent to collaborate with a human operator, completing tasks under safety constraints while maximally preserving human intent. However, existing methods often underperform in long-horizon tasks that require balancing task performance under sa
Large Audio-language Models (LAMs) have recently enabled powerful speech-based interactions by coupling audio encoders with Large Language Models (LLMs). However, the security of LAMs under adversarial attacks remains underexplored, especially through audio jailbreaks that craft malicious audio prom
Incorporating privacy regulations and business requirements, enterprises should securely manage unstructured textual data from diverse domains. Sensitive information classification is a critical component of data security, but it poses challenges due to complex textual contexts. With the ever-increa…
Large Language Models (LLMs) aligned with human feedback have recently garnered significant attention. However, it remains vulnerable to jailbreak attacks, where adversaries manipulate prompts to induce harmful outputs. Exploring jailbreak attacks enables us to investigate the vulnerabilities of LLM…