3 citations · 11 across the 25 of their papers we have counts for
28 papers
Representational alignment yields generalizable safety in language models
Lingyu Li, Yan Teng, Yingchun Wang +1
Aligning large language models (LLMs) is essential for their safe deployment. Current alignment methods mainly optimize observable responses, yet models remain vulnerable when the…
Long-Term Simulation Exposes Cognitive-Developmental Risks in AI Companions
Kaicheng Shen, Lingyu Li, Wen Wu +3
AI companions powered by large language models increasingly interact with cognition-developing users, including children and adolescents, creating risks that may accumulate over ti…
PseudoBench: Measuring How Agentic Auto-Research Fuels Pseudoscience
Xinyang Liao, Lingyu Li, Huacan Liu +5
As Large Language Model based agents enter autonomous scientific research, their ability to resist pseudoscience becomes increasingly important. Otherwise, such systems may rapidly…
SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
Jiaqi Yu, Xin Wang, Yixu Wang +4
Large language models increasingly stream long, reasoning-intensive responses in real time, making when to moderate as critical as whether to moderate. Existing guardrails fall int…
Towards Context-Invariant Safety Alignment for Large Language Models
Yixu Wang, Yang Yao, Xin Wang +4
Preference-based post-training aligns LLMs with human intent, yet safety behavior often remains brittle. A model may refuse a harmful request in a standard prompt but comply when t…
Mechanistic Origin of Moral Indifference in Language Models
Lingyu Li, Yan Teng, Yingchun Wang
Existing behavioral alignment techniques for Large Language Models (LLMs) often neglect the discrepancy between surface compliance and internal unaligned representations, leaving L…
From Sparse Decisions to Dense Reasoning: A Multi-attribute Trajectory Paradigm for Multimodal Moderation
Tianle Gu, Kexin Huang, Lingyu Li +6
Safety moderation is pivotal for identifying harmful content. Despite the success of textual safety moderation, its multimodal counterparts remain hindered by a dual sparsity of da…
OpenRT: An Open-Source Red Teaming Framework for Multimodal LLMs
Xin Wang, Yunhao Chen, Juncheng Li +7
The rapid integration of Multimodal Large Language Models (MLLMs) into critical applications is increasingly hindered by persistent safety vulnerabilities. However, existing red-te…
Evolve the Method, Not the Prompts: Evolutionary Synthesis of Jailbreak Attacks on LLMs
Yunhao Chen, Xin Wang, Juncheng Li +5
Automated red teaming frameworks for Large Language Models (LLMs) have become increasingly sophisticated, yet many still formulate attack optimization primarily in the prompt space…
GhostEI-Bench: Do Mobile Agents Resilience to Environmental Injection in Dynamic On-Device Environments?
Chiyu Chen, Xinhao Song, Yunkai Chai +7
Vision-Language Models (VLMs) are increasingly deployed as autonomous agents to navigate mobile graphical user interfaces (GUIs). Operating in dynamic on-device ecosystems, which i…
Dr. Bench: A Multidimensional Evaluation for Deep Research Agents, from Answers to Reports
Yang Yao, Yixu Wang, Yuxuan Zhang +9
As an embodiment of intelligence evolution toward interconnected architectures, Deep Research Agents (DRAs) systematically exhibit the capabilities in task decomposition, cross-sou…
StolenLoRA: Exploring LoRA Extraction Attacks via Synthetic Data
Yixu Wang, Yan Teng, Yingchun Wang +1
Parameter-Efficient Fine-Tuning (PEFT) methods like LoRA have transformed vision model adaptation, enabling the rapid deployment of customized models. However, the compactness of L…
FreezeVLA: Action-Freezing Attacks against Vision-Language-Action Models
Xin Wang, Jie Li, Zejia Weng +9
Vision-Language-Action (VLA) models are driving rapid progress in robotics by enabling agents to interpret multimodal inputs and execute complex, long-horizon tasks. However, their…
AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
Yixu Wang, Xin Wang, Yang Yao +5
The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-e…
LinguaSafe: A Comprehensive Multilingual Safety Benchmark for Large Language Models
Zhiyuan Ning, Tianle Gu, Jiaxin Song +8
The widespread adoption and increasing prominence of large language models (LLMs) in global technologies necessitate a rigorous focus on ensuring their safety across a diverse rang…
The Other Mind: How Language Models Exhibit Human Temporal Cognition
Lingyu Li, Yang Yao, Yixu Wang +3
As Large Language Models (LLMs) continue to advance, they exhibit certain cognitive patterns similar to those of humans that are not directly specified in training data. This study…
Probing the Robustness of Large Language Models Safety to Latent Perturbations
Tianle Gu, Kexin Huang, Zongqi Wang +7
Safety alignment is a key requirement for building reliable Artificial General Intelligence. Despite significant advances in safety alignment, we observe that minor latent shifts c…
SafeVid: Toward Safety Aligned Video Large Multimodal Models
Yixu Wang, Jiaxin Song, Yifeng Gao +6
As Video Large Multimodal Models (VLMMs) rapidly advance, their inherent complexity introduces significant safety challenges, particularly the issue of mismatched generalization wh…
JailBound: Jailbreaking Internal Safety Boundaries of Vision-Language Models
Jiaxin Song, Yixu Wang, Jie Li +4
Vision-Language Models (VLMs) exhibit impressive performance, yet the integration of powerful vision encoders has significantly broadened their attack surface, rendering them incre…
HoneypotNet: Backdoor Attacks Against Model Extraction
Yixu Wang, Tianle Gu, Yan Teng +2
Model extraction attacks are one type of inference-time attacks that approximate the functionality and performance of a black-box victim model by launching a certain number of quer…
IDEATOR: Jailbreaking and Benchmarking Large Vision-Language Models Using Themselves
Ruofan Wang, Juncheng Li, Yixu Wang +6
As large Vision-Language Models (VLMs) gain prominence, ensuring their safe deployment has become critical. Recent studies have explored VLM robustness against jailbreak attacks-te…
Reflection-Bench: Evaluating Epistemic Agency in Large Language Models
Lingyu Li, Yixu Wang, Haiquan Zhao +4
With large language models (LLMs) increasingly deployed as cognitive engines for AI agents, the reliability and effectiveness critically hinge on their intrinsic epistemic agency,…
MEOW: MEMOry Supervised LLM Unlearning Via Inverted Facts
Tianle Gu, Kexin Huang, Ruilin Luo +4
Large Language Models (LLMs) can memorize sensitive information, raising concerns about potential misuse. LLM Unlearning, a post-hoc approach to remove this information from traine…
MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
Tianle Gu, Zeyang Zhou, Kexin Huang +10
Powered by remarkable advancements in Large Language Models (LLMs), Multimodal Large Language Models (MLLMs) demonstrate impressive capabilities in manifold tasks. However, the pra…