19 citations · 67 across the 19 of their papers we have counts for
20 papers
Breaking the Myth: Can Small Models Infer Postconditions Too?
Gehao Zhang, Zhenting Wang, Juan Zhai
Formal specifications are essential for ensuring software correctness, yet manually writing them is tedious and error-prone. Large Language Models (LLMs) have shown promise in gene…
EDITOR: Effective and Interpretable Prompt Inversion for Text-to-Image Diffusion Models
Mingzhe Li, Kejing Xia, Gehao Zhang +5
Text-to-image generation models~(e.g., Stable Diffusion) have achieved significant advancements, enabling the creation of high-quality and realistic images based on textual descrip…
CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI
Siyuan Cheng, Lingjuan Lyu, Zhenting Wang +2
With the rapid advancement of generative AI, it is now possible to synthesize high-quality images in a few seconds. Despite the power of these technologies, they raise significant…
Continuous Concepts Removal in Text-to-image Diffusion Models
Tingxu Han, Weisong Sun, Yanrong Hu +6
Text-to-image diffusion models have shown an impressive ability to generate high-quality images from input textual descriptions. However, concerns have been raised about the potent…
Token-Budget-Aware LLM Reasoning
Tingxu Han, Zhenting Wang, Chunrong Fang +3
Reasoning is critical for large language models (LLMs) to excel in a wide range of tasks. While methods like Chain-of-Thought (CoT) reasoning and enhance LLM performance by decompo…
Towards Reliable Verification of Unauthorized Data Usage in Personalized Text-to-Image Diffusion Models
Boheng Li, Yanhao Wei, Yankai Fu +5
Text-to-image diffusion models are pushing the boundaries of what generative AI can achieve in our lives. Beyond their ability to generate general images, new personalization techn…
Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Hanrong Zhang, Jingyuan Huang, Kai Mei +5
Although LLM-based agents, powered by Large Language Models (LLMs), can use external tools and memory mechanisms to solve complex real-world tasks, they may also introduce critical…
Data-centric NLP Backdoor Defense from the Lens of Memorization
Zhenting Wang, Zhizhi Wang, Mingyu Jin +3
Backdoor attack is a severe threat to the trustworthiness of DNN-based language models. In this paper, we first extend the definition of memorization of language models from sample…
An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer
Weipeng Jiang, Zhenting Wang, Juan Zhai +3
Despite prior safety alignment efforts, mainstream LLMs can still generate harmful and unethical content when subjected to jailbreaking attacks. Existing jailbreaking methods fall…
Evaluating and Mitigating IP Infringement in Visual Generative AI
Zhenting Wang, Chen Chen, Vikash Sehwag +2
The popularity of visual generative AI models like DALL-E 3, Stable Diffusion XL, Stable Video Diffusion, and Sora has been increasing. Through extensive evaluation, we discovered…
How to Trace Latent Generative Model Generated Images without Artificial Watermark?
Zhenting Wang, Vikash Sehwag, Chen Chen +3
Latent generative models (e.g., Stable Diffusion) have become more and more popular, but concerns have arisen regarding potential misuse related to images generated by these models…
Invisible Backdoor Attack against Self-supervised Learning
Hanrong Zhang, Zhenting Wang, Boheng Li +7
Self-supervised learning (SSL) models are vulnerable to backdoor attacks. Existing backdoor attacks that are effective in SSL often involve noticeable triggers, like colored patche…
Alteration-free and Model-agnostic Origin Attribution of Generated Images
Zhenting Wang, Chen Chen, Yi Zeng +2
Recently, there has been a growing attention in image generation models. However, concerns have emerged regarding potential misuse and intellectual property (IP) infringement assoc…
NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models
Kai Mei, Zheng Li, Zhenting Wang +2
Prompt-based learning is vulnerable to backdoor attacks. Existing backdoor attacks against prompt-based models consider injecting backdoors into the entire embedding layers or word…
UNICORN: A Unified Backdoor Trigger Inversion Framework
Zhenting Wang, Kai Mei, Juan Zhai +1
The backdoor attack, where the adversary uses inputs stamped with triggers (e.g., a patch) to activate pre-planted malicious behaviors, is a severe threat to Deep Neural Network (D…
Backdoor Vulnerabilities in Normally Trained Deep Learning Models
Guanhong Tao, Zhenting Wang, Siyuan Cheng +7
We conduct a systematic study of backdoor vulnerabilities in normally trained Deep Learning models. They are as dangerous as backdoors injected by data poisoning because both can b…
Rethinking the Reverse-engineering of Trojan Triggers
Zhenting Wang, Kai Mei, Hailun Ding +2
Deep Neural Networks are vulnerable to Trojan (or backdoor) attacks. Reverse-engineering methods can reconstruct the trigger and thus identify affected models. Existing reverse-eng…
BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning
Zhenting Wang, Juan Zhai, Shiqing Ma
Deep neural networks are vulnerable to Trojan attacks. Existing attacks use visible patterns (e.g., a patch or image transformations) as triggers, which are vulnerable to human ins…
Training with More Confidence: Mitigating Injected and Natural Backdoors During Training
Zhenting Wang, Hailun Ding, Juan Zhai +1
The backdoor or Trojan attack is a severe threat to deep neural networks (DNNs). Researchers find that DNNs trained on benign data and settings can also learn backdoor behaviors, w…
EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry
Yingqi Liu, Guangyu Shen, Guanhong Tao +3
Backdoor attack injects malicious behavior to models such that inputs embedded with triggers are misclassified to a target label desired by the attacker. However, natural features…