42 citations · 139 across the 48 of their papers we have counts for
53 papers
ASCENT: First-Order Optimal Fine-Tuning with Recalibration for Safety--Utility Co-Enhancement
Weiwei Qi, Chongyu Wang, Tianhang Zheng +5
Supervised fine-tuning can substantially improve the downstream utility of large language models (LLMs) but may compromise their safety. Existing safety-preserving methods constrai…
ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents
Hongwei Yao, Yiming Liu, Meihui Chen +6
Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API. We define behavioral safety and introduce ActBe…
DARWIN: Evolving Jailbreak Adversary and Guardrail for LLM Safety Evaluation and Protection
Weiwei Qi, Zefeng Wu, Zhilin Guo +5
Most existing LLM safety evaluation and defense methods are static: jailbreak vulnerabilities are assessed with fixed attacks, and guardrails are trained on fixed malicious-prompt…
DataShield: Uncovering Risky Fine-Tuning Data Across LLMs Through Consensus Subspace Alignment
Zefeng Wu, Weiwei Qi, Jielong Chen +6
Fine-tuning large language models (LLMs) on domain-specific datasets has become a standard paradigm for adapting LLMs to specialized applications. However, recent work has shown th…
TRACE: Task-Aware Adaptive Self-Evolving Agentic Jailbreaking
Churui Zeng, Weiwei Qi, Kedong Xiu +6
The rise of LLM agents introduces a new threat by enabling planning, coding, and even end-to-end execution of expert-level attack workflows. However, this threat remains underexplo…
Towards Identification and Intervention of Safety-Critical Parameters in Large Language Models
Weiwei Qi, Zefeng Wu, Tianhang Zheng +4
Ensuring Large Language Model (LLM) safety is crucial, yet the lack of a clear understanding about safety mechanisms hinders the development of precise and reliable methodologies f…
JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization
Haolun Zheng, Yu He, Tailun Chen +6
Text-to-image (T2I) models such as Stable Diffusion and DALLE remain susceptible to generating harmful or Not-Safe-For-Work (NSFW) content under jailbreak attacks despite deployed…
Towards Cross-lingual Values Judgment: A Consensus-Pluralism Perspective
Yukun Chen, Xinyu Zhang, Boyi Deng +6
As large language models (LLMs) are employed worldwide, existing evaluation paradigms for their multilingual capabilities primarily focus on factual task performance, neglecting th…
Explainable Token-level Noise Filtering for LLM Fine-tuning Datasets
Yuchen Yang, Wenze Lin, Enhao Huang +6
Large Language Models (LLMs) have seen remarkable advancements, achieving state-of-the-art results in diverse applications. Fine-tuning, an important step for adapting LLMs to spec…
DualMind: Towards Understanding Cognitive-Affective Cascades in Public Opinion Dissemination via Multi-Agent Simulation
Enhao Huang, Tongtong Pan, Shuhuai Zhang +6
Forecasting public opinion during PR crises is challenging, as existing frameworks often overlook the interaction between transient affective responses and persistent cognitive bel…
SpatialJB: How Text Distribution Art Becomes the "Jailbreak Key" for LLM Guardrails
Zhiyi Mou, Jingyuan Yang, Zeheng Qian +6
While Large Language Models (LLMs) have powerful capabilities, they remain vulnerable to jailbreak attacks, which is a critical barrier to their safe web real-time application. Cur…
NonTextual Target Attack
Xinzhe Huang, Wenjing Hu, Tianhang Zheng +6
Existing gradient-based jailbreak attacks on Large Language Models (LLMs) typically optimize adversarial suffixes to align the LLM output with predefined target responses. However,…
Dynamic Jailbreaking Attack
Kedong Xiu, Yunhan Yang, Churui Zeng +6
Existing gradient-based jailbreak attacks typically optimize a fixed-length adversarial suffix toward a predefined target response with a static optimization strategy. However, thi…
Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack
Yukun Chen, Boheng Li, Yu Yuan +5
Knowledge distillation (KD) is a vital technique for deploying deep neural networks (DNNs) on resource-constrained devices by transferring knowledge from large teacher models to li…
HarmMetric Eval: Benchmarking Metrics and Judges for LLM Harmfulness Assessment
Langqi Yang, Tianhang Zheng, Yixuan Chen +6
The potential of large language models (LLMs) to generate harmful content poses a significant safety risk for data management, as LLMs are increasingly being used as engines for da…
Module-Aware Parameter-Efficient Machine Unlearning on Transformers
Wenjie Bao, Jian Lou, Yuke Hu +5
Transformer has become fundamental to a vast series of pre-trained large models that have achieved remarkable success across diverse applications. Machine unlearning, which focuses…
MAJIC: Markovian Adaptive Jailbreaking via Iterative Composition of Diverse Innovative Strategies
Weiwei Qi, Shuo Shao, Wei Gu +4
Large Language Models (LLMs) have exhibited remarkable capabilities but remain vulnerable to jailbreaking attacks, which can elicit harmful content from the models by manipulating…
Towards Evaluation for Real-World LLM Unlearning
Ke Miao, Yuke Hu, Xiaochen Li +4
This paper analyzes the limitations of existing unlearning evaluation metrics in terms of practicality, exactness, and robustness in real-world LLM unlearning scenarios. To overcom…
Towards Mitigating Excessive Forgetting in LLM Unlearning via Entanglement-Guidance with Proxy Constraint
Zhihao Liu, Jian Lou, Yuke Hu +6
Large language models (LLMs) are trained on massive datasets that may include private or copyrighted content. Due to growing privacy and ownership concerns, data owners may request…
ContextCache: Context-Aware Semantic Cache for Multi-Turn Queries in Large Language Models
Jianxin Yan, Wangze Ni, Lei Chen +4
Semantic caching significantly reduces computational costs and improves efficiency by storing and reusing large language model (LLM) responses. However, existing systems rely prima…
Rethinking Data Protection in the (Generative) Artificial Intelligence Era
Yiming Li, Shuo Shao, Yu He +8
The (generative) artificial intelligence (AI) era has profoundly reshaped the meaning and value of data. No longer confined to static content, data now permeates every stage of the…
SmartGuard: Leveraging Large Language Models for Network Attack Detection through Audit Log Analysis and Summarization
Hao Zhang, Shuo Shao, Song Li +3
End-point monitoring solutions are widely deployed in today's enterprise environments to support advanced attack detection and investigation. These monitors continuously record sys…
Towards Label-Only Membership Inference Attack against Pre-trained Large Language Models
Yu He, Boheng Li, Liu Liu +6
Membership Inference Attacks (MIAs) aim to predict whether a data sample belongs to the model's training set or not. Although prior research has extensively explored MIAs in Large…
REFINE: Inversion-Free Backdoor Defense via Model Reprogramming
Yukun Chen, Shuo Shao, Enhao Huang +4
Backdoor attacks on deep neural networks (DNNs) have emerged as a significant security threat, allowing adversaries to implant hidden malicious behaviors during the model training…