papers

Publications (25)

cs.CR2026

Stego Battlefield: Evaluating Image Steganography Attacks and Steganalysis Defenses

Zhen Sun, Zongmin Zhang, Leyi Sheng +7

Image steganography is widely used to protect user privacy and enable covert communication. However, it can also be abused by the adversary as a covert channel to bypass content mo…

cs.CY2025

Humanizing LLMs: A Survey of Psychological Measurements with Tools, Datasets, and Human-Agent Applications

Wenhan Dong, Yuemeng Zhao, Zhen Sun +10

As large language models (LLMs) are increasingly used in human-centered tasks, assessing their psychological traits is crucial for understanding their social impact and ensuring tr…

cs.CE2026

TxSum: User-Centered Ethereum Transaction Understanding with Micro-Level Semantic Grounding

Zifan Peng, Jingyi Zheng, Yule Liu +8

Understanding the economic intent of Ethereum transactions is critical for user safety, yet current tools expose only raw on-chain data or surface-level intent, leading to widespre…

cs.CL2025

Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models

Yule Liu, Jingyi Zheng, Zhen Sun +6

Recent advancements in large reasoning models (LRMs) have demonstrated the effectiveness of scaling test-time computation to enhance reasoning capabilities on various tasks. Howeve…

cs.AI2026

Chain-of-Authorization: Embedding authorization into large language models

Yang Li, Yule Liu, Xinlei He +3

Although Large Language Models (LLMs) have evolved from text generators into the cognitive core of modern AI systems, their inherent lack of authorization awareness exposes these s…

cs.CR2025

TH-Bench: Evaluating Evading Attacks via Humanizing AI Text on Machine-Generated Text Detectors

Jingyi Zheng, Junfeng Wang, Zhen Sun +3

As Large Language Models (LLMs) advance, Machine-Generated Texts (MGTs) have become increasingly fluent, high-quality, and informative. Existing wide-range MGT detectors are design…

cs.CR2026

JALMBench: Benchmarking Jailbreak Vulnerabilities in Audio Language Models

Zifan Peng, Yule Liu, Zhen Sun +9

Large Audio Language Models (LALMs) have made significant progress. While increasingly deployed in real-world applications, LALMs face growing safety risks from jailbreak attacks t…

cs.AI2025

On the Generalization and Adaptation Ability of Machine-Generated Text Detectors in Academic Writing

Yule Liu, Zhiyuan Zhong, Yifan Liao +8

The rising popularity of large language models (LLMs) has raised concerns about machine-generated text (MGT), particularly in academic settings, where issues like plagiarism and mi…

cs.CR2025

Unsafe LLM-Based Search: Quantitative Analysis and Mitigation of Safety Risks in AI Web Search

Zeren Luo, Zifan Peng, Yule Liu +4

Recent advancements in Large Language Models (LLMs) have significantly enhanced the capabilities of AI-Powered Search Engines (AIPSEs), offering precise and efficient responses by…

cs.CR2026

Auditing Data Membership in Reinforcement Learning With Verifiable Rewards

Yule Liu, Heyi Zhang, Jinyi Zheng +6

Reinforcement Learning with Verifiable Rewards (RLVR) has become a core training stage in recent large language models (LLMs). Its reliance on non-public, high-value prompt sets ra…

cs.CR2024

Jailbreak Attacks and Defenses Against Large Language Models: A Survey

Sibo Yi, Yule Liu, Zhen Sun +5

Large Language Models (LLMs) have performed exceptionally in various text-generative tasks, including question answering, translation, code completion, etc. However, the over-assis…

cs.CL2025

ZPD-SCA: Unveiling the Blind Spots of LLMs in Assessing Students' Cognitive Abilities

Wenhan Dong, Zhen Sun, Yuemeng Zhao +9

Large language models (LLMs) have demonstrated potential in educational applications, yet their capacity to accurately assess the cognitive alignment of reading materials with stud…

cs.AI2025

Are We in the AI-Generated Text World Already? Quantifying and Monitoring AIGT on Social Media

Zhen Sun, Zongmin Zhang, Xinyue Shen +5

Social media platforms are experiencing a growing presence of AI-Generated Texts (AIGTs). However, the misuse of AIGTs could have profound implications for public opinion, such as…

cs.LG2026

CHASM: Unveiling Covert Advertisements on Chinese Social Media

Jingyi Zheng, Tianyi Hu, Yule Liu +5

Current benchmarks for evaluating large language models (LLMs) in social media moderation completely overlook a serious threat: covert advertisements, which disguise themselves as…

cs.CR2025

"To Survive, I Must Defect": Jailbreaking LLMs via the Game-Theory Scenarios

Zhen Sun, Zongmin Zhang, Deqi Liang +8

As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-cr…

cs.CR2024

Quantized Delta Weight Is Safety Keeper

Yule Liu, Zhen Sun, Xinlei He +1

Recent advancements in fine-tuning proprietary language models enable customized applications across various domains but also introduce two major challenges: high resource demands…

cs.CL2025

Evaluation Hallucination in Multi-Round Incomplete Information Lateral-Driven Reasoning Tasks

Wenhan Dong, Tianyi Hu, Jingyi Zheng +5

Multi-round incomplete information tasks are crucial for evaluating the lateral thinking capabilities of large language models (LLMs). Currently, research primarily relies on multi…

cs.CL2026

AtomEval: Validity-Aware Atomic Evaluation of Adversarial Claim Rewriting in Fact Verification

Hongyi Cen, Mingxin Wang, Yule Liu +3

Large language models (LLMs) can rewrite refuted claims to evade evidence-based fact verifiers, but conventional attack success rate (ASR) can be inflated when rewrites change, wea…

cs.CR2026

Escaping the Linearity Trap: Manifold Detours for Black-Box Adversarial Attacks on Singing Audio Deepfake Detection

Yifan Liao, Yule Liu, Zhen Sun +5

Recent Singing Voice Synthesis (SVS) advances enable highly realistic but potentially malicious AI covers, making singing voice deepfake detection (SVDD) crucial. Self-Supervised L…

cs.CR2026

A Watermark for Vision-Language-Action and World Action Models

Yule Liu, Shuai Liu, Jiaheng Wei +1

Vision-language-action (VLA) models and world-action models (WAM) are the generative models now driving general-purpose robot control, turning raw camera input directly into motor…

cs.CR2026

What Your Posts Reveal: A Benchmark and Agentic Framework for User-Level Privacy Leakage on Social Media

Zifan Peng, Yini Huang, Aiwen Lu +7

Public social media posts can reveal private information through weak cues scattered across text, images, or metadata. Such leakage is often cumulative and cross-post: cues that ap…

cs.CR2025

PEFTGuard: Detecting Backdoor Attacks Against Parameter-Efficient Fine-Tuning

Zhen Sun, Tianshuo Cong, Yule Liu +5

Fine-tuning is an essential process to improve the performance of Large Language Models (LLMs) in specific domains, with Parameter-Efficient Fine-Tuning (PEFT) gaining popularity d…

cs.CR2026

On the Generation and Mitigation of Harmful Geometry in Image-to-3D Models

Yule Liu, Yilong Yang, Jiale Teng +11

Recent advances in image-to-3D models have significantly improved the fidelity and accessibility of 3D content creation. Such a powerful reconstruction capability that enables crea…

cs.AI2025

GasAgent: A Multi-Agent Framework for Automated Gas Optimization in Smart Contracts

Jingyi Zheng, Zifan Peng, Yule Liu +4

Smart contracts are trustworthy, immutable, and automatically executed programs on the blockchain. Their execution requires the Gas mechanism to ensure efficiency and fairness. How…

cs.CR2025

SoK: Benchmarking Poisoning Attacks and Defenses in Federated Learning

Heyi Zhang, Yule Liu, Xinlei He +3

Federated learning (FL) enables collaborative model training while preserving data privacy, but its decentralized nature exposes it to client-side data poisoning attacks (DPAs) and…