Papers by Kuofeng Gao
Your Language Model Can Secretly Write Like Humans: Contrastive Paraphrase Attacks on LLM-Generated Text Detectors (2025.emnlp-main)
Copied to clipboard
Hao Fang, Jiawei Kong, Tianqu Zhuang, Yixiang Qiu, Kuofeng Gao, Bin Chen, Shu-Tao Xia, Yaowei Wang, Min Zhang
| Challenge: | Existing methods to detect large language models (LLMs) generated for plagiarism use paraphrases to rewrite them to evade detection. |
| Approach: | They propose a training-free method that effectively fools text detectors using off-the-shelf LLMs by rewriting them to evade detection. |
| Outcome: | The proposed method deceives text detectors using off-the-shelf LLMs by rewriting them to produce human-like sentences that are less discernible by detectors. |
Retrievals Can Be Detrimental: Unveiling the Backdoor Vulnerability of Retrieval-Augmented Diffusion Models (2026.acl-long)
Copied to clipboard
| Challenge: | Retrieval-augmented diffusion models (RDMs) have been developed to enhance performance with reduced parameters. |
| Approach: | They propose to integrate retrieval-augmented diffusion models with Retrieval-augmented generation (RAG) that enhances performance with reduced parameters. |
| Outcome: | The proposed framework achieves outstanding attack effects while maintaining benign utility. |
Benchmarking Open-ended Audio Dialogue Understanding for Large Audio-Language Models (2025.acl-long)
Copied to clipboard
| Challenge: | Large Audio-Language Models (LALMs) have recently unlocked audio dialogue capabilities, enabling direct spoken exchanges with humans. |
| Approach: | They propose to evaluate LALMs' open-ended audio dialogue ability in 3 general scenarios, 12 skills, 9 multilingual languages, and 4 categories of ambiguity handling. |
| Outcome: | The proposed benchmark assesses the open-ended audio dialogue ability for LALMs in 3 general scenarios, 12 skills, 9 multilingual languages, and 4 categories of ambiguity handling. |
When Efficiency Meets Safety: A Benchmark Security Analysis of KV Cache Compression in Large Language Models (2026.acl-long)
Copied to clipboard
| Challenge: | Key-Value (KV) caching is widely used in large language models to enable long-context inference efficiently, yet its security implications remain underexplored. |
| Approach: | They propose a history-aware, per-head feedback merging strategy that prevents safety degradation while maintaining efficiency. |
| Outcome: | The proposed strategy prevents safety degradation while maintaining efficiency. |
Infinite Babble: Inflating 3D Vision-Language Model Inference Overhead via Adversarial Geometric Perturbation (2026.findings-acl)
Copied to clipboard
| Challenge: | 3D Vision-Language Models (VLMs) are critical cognitive backbone for spatial intelligence, but their reliance on autoregressive decoding introduces a fundamental vulnerability regarding inference efficiency. |
| Approach: | They propose a framework that triggers computational and economic exhaustion in 3D-VLMs by injecting imperceptible noise that forces the model into a state of pathological verbosity. |
| Outcome: | The proposed framework amplifies output length and energy consumption by up to 6.45, demonstrating a potent capability to drain system resources. |
VLMInferSlow: Evaluating the Efficiency Robustness of Large Vision-Language Models as a Service (2025.acl-long)
Copied to clipboard
| Challenge: | Existing studies evaluate efficiency robustness of vision-language models under unrealistic assumptions, requiring access to model architecture and parameters. |
| Approach: | They propose a novel approach to evaluate VLM efficiency robustness in a realistic black-box setting. |
| Outcome: | The proposed approach generates adversarial images with imperceptible perturbations, increasing the computational cost by up to 128.47%. |
Pre-training CLIP against Data Poisoning with Optimal Transport-based Matching and Alignment (2025.emnlp-main)
Copied to clipboard
| Challenge: | Recent studies have shown that Contrastive Language-Image Pre-training (CLIP) models are vulnerable to data poisoning and backdoor attacks due to massive training image-caption pairs crawled from the Internet. |
| Approach: | They propose an Optimal Transport-based framework to reconstruct image-caption pairs and propose an optimal transport-based distance measure to re-assign new captions based on the proposed optimal transport distance. |
| Outcome: | The proposed framework reduces the attack success rates of poisoning attacks to 0% in most cases. |
QueryAttack: Jailbreaking Aligned Large Language Models Using Structured Non-natural Query Language (2025.findings-acl)
Copied to clipboard
Qingsong Zou, Jingyu Xiao, Qing Li, Zhi Yan, Yuhang Wang, Li Xu, Wenxuan Wang, Kuofeng Gao, Ruoyu Li, Yong Jiang
| Challenge: | Existing methods to bypass security defenses of large language models (LLMs) are not effective, but QueryAttack can be jailbroken. |
| Approach: | They propose a framework to examine generalizability of safety alignment by translating malicious queries into structured non-natural query languages. |
| Outcome: | The proposed framework can achieve high attack success rates and jailbreak various defense methods on mainstream LLMs. |