5 papers
NEXUS: Learning Safety Constraints and Action Models for Safe and Robust Embodied Planning
Tiehan Cui, Peipei Liu, Yanxu Mao +4
Large language models (LLMs) enable embodied agents to plan from naturallanguage instructions, yet their actions may be physically infeasible or hazardous. Existing neuro-symbolic…
Stop Fixating on Prompts: Reasoning Hijacking and Constraint Tightening for Red-Teaming LLM Agents
Yanxu Mao, Peipei Liu, Tiehan Cui +3
With the widespread application of LLM-based agents across various domains, their complexity has introduced new security threats. Existing red-team methods mostly rely on modifying…
From LLMs to MLLMs to Agents: A Survey of Emerging Paradigms in Jailbreak Attacks and Defenses within LLM Ecosystem
Yanxu Mao, Tiehan Cui, Peipei Liu +2
Large language models (LLMs) are rapidly evolving from single-modal systems to multimodal LLMs and intelligent agents, significantly expanding their capabilities while introducing…
Exploring Jailbreak Attacks on LLMs through Intent Concealment and Diversion
Tiehan Cui, Yanxu Mao, Peipei Liu +2
Although large language models (LLMs) have achieved remarkable advancements, their security remains a pressing concern. One major threat is jailbreak attacks, where adversarial pro…
Low-Resource Fast Text Classification Based on Intra-Class and Inter-Class Distance Calculation
Yanxu Mao, Peipei Liu, Tiehan Cui +2
In recent years, text classification methods based on neural networks and pre-trained models have gained increasing attention and demonstrated excellent performance. However, these…