Junjie Chu

Junjie Chu, Yiting Qu, Ye Leng et al.

Large Language Models (LLMs) are increasingly trained to align with human values, primarily focusing on task level, i.e., refusing to execute directly harmful tasks. However, a subtle yet crucial content-level ethical question is often overlooked: when performing a seemingly benign task, will LLMs -- like morally conscious human beings -- refuse to proceed when encountering harmful content in user-provided material? In this study, we aim to understand this content-level ethical question and systematically evaluate its implications for mainstream LLMs. We first construct a harmful knowledge dataset (i.e., non-compliant with OpenAI's usage policy) to serve as the user-supplied harmful content, with 1,357 entries across ten harmful categories. We then design nine harmless tasks (i.e., compliant with OpenAI's usage policy) to simulate the real-world benign tasks, grouped into three categories according to the extent of user-supplied content required: extensive, moderate, and limited. Leveraging the harmful knowledge dataset and the set of harmless tasks, we evaluate how nine LLMs behave when exposed to user-supplied harmful content during the execution of benign tasks, and further examine how the dynamics between harmful knowledge categories and tasks affect different LLMs. Our results show that current LLMs, even the latest GPT-5.2 and Gemini-3-Pro, often fail to uphold human-aligned ethics by continuing to process harmful content in harmless tasks. Furthermore, external knowledge from the ``Violence/Graphic'' category and the ``Translation'' task is more likely to elicit harmful responses from LLMs. We also conduct extensive ablation studies to investigate potential factors affecting this novel misuse vulnerability. We hope that our study could inspire enhanced safety measures among stakeholders to mitigate this overlooked content-level ethical risk.

Atilla Akkus, Masoud Poorghaffar Aghdam, Mingjie Li et al.

Large language models (LLMs) have demonstrated significant success in various domain-specific tasks, with their performance often improving substantially after fine-tuning. However, fine-tuning with real-world data introduces privacy risks. To mitigate these risks, developers increasingly rely on synthetic data generation as an alternative to using real data, as data generated by traditional models is believed to be different from real-world data. However, with the advanced capabilities of LLMs, the distinction between real data and data generated by these models has become nearly indistinguishable. This convergence introduces similar privacy risks for generated data to those associated with real data. Our study investigates whether fine-tuning with LLM-generated data truly enhances privacy or introduces additional privacy risks by examining the structural characteristics of data generated by LLMs, focusing on two primary fine-tuning approaches: supervised fine-tuning (SFT) with unstructured (plain-text) generated data and self-instruct tuning. In the scenario of SFT, the data is put into a particular instruction tuning format used by previous studies. We use Personal Information Identifier (PII) leakage and Membership Inference Attacks (MIAs) on the Pythia Model Suite and Open Pre-trained Transformer (OPT) to measure privacy risks. Notably, after fine-tuning with unstructured generated data, the rate of successful PII extractions for Pythia increased by over 20%, highlighting the potential privacy implications of such approaches. Furthermore, the ROC-AUC score of MIAs for Pythia-6.9b, the second biggest model of the suite, increases over 40% after self-instruct tuning. Our results indicate the potential privacy risks associated with fine-tuning LLMs using generated data, underscoring the need for careful consideration of privacy safeguards in such approaches.

Ye Leng, Junjie Chu, Mingjie Li et al.

Recently, multimodal large language models (MLLMs) have emerged as a unified paradigm for language and image generation. Compared with diffusion models, MLLMs possess a much stronger capability for semantic understanding, enabling them to process more complex textual inputs and comprehend richer contextual meanings. However, this enhanced semantic ability may also introduce new and potentially greater safety risks. Taking diffusion models as a reference point, we systematically analyze and compare the safety risks of emerging MLLMs along two dimensions: unsafe content generation and fake image synthesis. Across multiple unsafe generation benchmark datasets, we observe that MLLMs tend to generate more unsafe images than diffusion models. This difference partly arises because diffusion models often fail to interpret abstract prompts, producing corrupted outputs, whereas MLLMs can comprehend these prompts and generate unsafe content. For current advanced fake image detectors, MLLM-generated images are also notably harder to identify. Even when detectors are retrained with MLLMs-specific data, they can still be bypassed by simply providing MLLMs with longer and more descriptive inputs. Our measurements indicate that the emerging safety risks of the cutting-edge generative paradigm, MLLMs, have not been sufficiently recognized, posing new challenges to real-world safety.

Junjie Chu, Prashant Singh, Salman Toor

In the past few decades, the rapid development of information and internet technologies has spawned massive amounts of data and information. The information explosion drives many enterprises or individuals to seek to rent cloud computing infrastructure to put their applications in the cloud. However, the agreements reached between cloud computing providers and clients are often not efficient. Many factors affect the efficiency, such as the idleness of the providers' cloud computing infrastructure, and the additional cost to the clients. One possible solution is to introduce a comprehensive, bargaining game (a type of negotiation), and schedule resources according to the negotiation results. We propose an agent-based auto-negotiation system for resource scheduling based on fuzzy logic. The proposed method can complete a one-to-one auto-negotiation process and generate optimal offers for the provider and client. We compare the impact of different member functions, fuzzy rule sets, and negotiation scenario cases on the offers to optimize the system. It can be concluded that our proposed method can utilize resources more efficiently and is interpretable, highly flexible, and customizable. We successfully train machine learning models to replace the fuzzy negotiation system to improve processing speed. The article also highlights possible future improvements to the proposed system and machine learning models. All the codes and data are available in the open-source repository.

Junjie Chu, Yugeng Liu, Ziqing Yang et al.

Jailbreak attacks aim to bypass the LLMs' safeguards. While researchers have proposed different jailbreak attacks in depth, they have done so in isolation -- either with unaligned settings or comparing a limited range of methods. To fill this gap, we present a large-scale evaluation of various jailbreak attacks. We collect 17 representative jailbreak attacks, summarize their features, and establish a novel jailbreak attack taxonomy. Then we conduct comprehensive measurement and ablation studies across nine aligned LLMs on 160 forbidden questions from 16 violation categories. Also, we test jailbreak attacks under eight advanced defenses. Based on our taxonomy and experiments, we identify some important patterns, such as heuristic-based attacks could achieve high attack success rates but are easy to mitigate by defenses, causing low practicality. Our study offers valuable insights for future research on jailbreak attacks and defenses. We hope our work could help the community avoid incremental work and serve as an effective benchmark tool for practitioners.

Junjie Chu, Zeyang Sha, Michael Backes et al.

Significant advancements have recently been made in large language models represented by GPT models. Users frequently have multi-round private conversations with cloud-hosted GPT models for task optimization. Yet, this operational paradigm introduces additional attack surfaces, particularly in custom GPTs and hijacked chat sessions. In this paper, we introduce a straightforward yet potent Conversation Reconstruction Attack. This attack targets the contents of previous conversations between GPT models and benign users, i.e., the benign users' input contents during their interaction with GPT models. The adversary could induce GPT models to leak such contents by querying them with designed malicious prompts. Our comprehensive examination of privacy risks during the interactions with GPT models under this attack reveals GPT-4's considerable resilience. We present two advanced attacks targeting improved reconstruction of past conversations, demonstrating significant privacy leakage across all models under these advanced techniques. Evaluating various defense mechanisms, we find them ineffective against these attacks. Our findings highlight the ease with which privacy can be compromised in interactions with GPT models, urging the community to safeguard against potential abuses of these models' capabilities.

Junjie Chu, Xinyue Shen, Ye Leng et al.

The rapid growth of research in LLM safety makes it hard to track all advances. Benchmarks are therefore crucial for capturing key trends and enabling systematic comparisons. Yet, it remains unclear why certain benchmarks gain prominence, and no systematic assessment has been conducted on their academic influence or code quality. This paper fills this gap by presenting the first multi-dimensional evaluation of the influence (based on five metrics) and code quality (based on both automated and human assessment) on LLM safety benchmarks, analyzing 31 benchmarks and 382 non-benchmarks across prompt injection, jailbreak, and hallucination. We find that benchmark papers show no significant advantage in academic influence (e.g., citation count and density) over non-benchmark papers. We uncover a key misalignment: while author prominence correlates with paper influence, neither author prominence nor paper influence shows a significant correlation with code quality. Our results also indicate substantial room for improvement in code and supplementary materials: only 39% of repositories are ready-to-use, 16% include flawless installation guides, and a mere 6% address ethical considerations. Given that the work of prominent researchers tends to attract greater attention, they need to lead the effort in setting higher standards.

Junjie Chu, Mingjie Li, Ziqing Yang et al.

Accurately determining whether a jailbreak attempt has succeeded is a fundamental yet unresolved challenge. Existing evaluation methods rely on misaligned proxy indicators or naive holistic judgments. They frequently misinterpret model responses, leading to inconsistent and subjective assessments that misalign with human perception. To address this gap, we introduce JADES (Jailbreak Assessment via Decompositional Scoring), a universal jailbreak evaluation framework. Its key mechanism is to automatically decompose an input harmful question into a set of weighted sub-questions, score each sub-answer, and weight-aggregate the sub-scores into a final decision. JADES also incorporates an optional fact-checking module to strengthen the detection of hallucinations in jailbreak responses. We validate JADES on JailbreakQR, a newly introduced benchmark proposed in this work, consisting of 400 pairs of jailbreak prompts and responses, each meticulously annotated by humans. In a binary setting (success/failure), JADES achieves 98.5% agreement with human evaluators, outperforming strong baselines by over 9%. Re-evaluating five popular attacks on four LLMs reveals substantial overestimation (e.g., LAA's attack success rate on GPT-3.5-Turbo drops from 93% to 69%). Our results show that JADES could deliver accurate, consistent, and interpretable evaluations, providing a reliable basis for measuring future jailbreak attacks.