19 citations · 29 across the 8 of their papers we have counts for
9 papers
Attention is All You Need to Defend Against Indirect Prompt Injection Attacks in LLMs
Yinan Zhong, Qianhao Miao, Yanjiao Chen +3
Large Language Models (LLMs) have been integrated into many applications (e.g., web agents) to perform more sophisticated tasks. However, LLM-empowered applications are vulnerable…
Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries
Xinfeng Li, Shengyuan Pang, Jialin Wu +5
Text-to-image (T2I) models, though exhibiting remarkable creativity in image generation, can be exploited to produce unsafe images. Existing safety measures, e.g., content moderati…
Protego: Detecting Adversarial Examples for Vision Transformers via Intrinsic Capabilities
Jialin Wu, Kaikai Pan, Yanjiao Chen +3
Transformer models have excelled in natural language tasks, prompting the vision community to explore their implementation in computer vision problems. However, these models are st…
Legilimens: Practical and Unified Content Moderation for Large Language Model Services
Jialin Wu, Jiangyi Deng, Shengyuan Pang +4
Given the societal impact of unsafe content generated by large language models (LLMs), ensuring that LLM services comply with safety standards is a crucial concern for LLM service…
RACONTEUR: A Knowledgeable, Insightful, and Portable LLM-Powered Shell Command Explainer
Jiangyi Deng, Xinfeng Li, Yanjiao Chen +5
Malicious shell commands are linchpins to many cyber-attacks, but may not be easy to understand by security analysts due to complicated and often disguised code structures. Advance…
SOPHON: Non-Fine-Tunable Learning to Restrain Task Transferability For Pre-trained Models
Jiangyi Deng, Shengyuan Pang, Yanjiao Chen +4
Instead of building deep learning models from scratch, developers are more and more relying on adapting pre-trained models to their customized tasks. However, powerful pre-trained…
SafeGen: Mitigating Sexually Explicit Content Generation in Text-to-Image Models
Xinfeng Li, Yuchen Yang, Jiangyi Deng +4
Text-to-image (T2I) models, such as Stable Diffusion, have exhibited remarkable performance in generating high-quality images from text descriptions in recent years. However, text-…
Catch You and I Can: Revealing Source Voiceprint Against Voice Conversion
Jiangyi Deng, Yanjiao Chen, Yinan Zhong +3
Voice conversion (VC) techniques can be abused by malicious parties to transform their audios to sound like a target speaker, making it hard for a human being or a speaker verifica…
V-Cloak: Intelligibility-, Naturalness- & Timbre-Preserving Real-Time Voice Anonymization
Jiangyi Deng, Fei Teng, Yanjiao Chen +3
Voice data generated on instant messaging or social media applications contains unique user voiceprints that may be abused by malicious adversaries for identity inference or identi…