1 citations · 2 across the 19 of their papers we have counts for
20 papers
Can Prompt Anonymity Protect Your Identity From LLM Providers?
Dzung Pham, Dillon Sheils, Naina Singh +1
User conversations with large language models (LLMs) often contain highly sensitive personal information that can be exploited by LLM providers to create detailed user dossiers, en…
DuplexJail: Spoken Interruption Attacks on Full-Duplex Speech Models
Jaechul Roh, Deepak Chandran, Amir Houmansadr +1
Full-duplex speech models accept user speech while generating responses, making input timing a potential safety concern. We introduce DuplexJail, which delivers fixed, request-inde…
Whose Agent Are You? Multi-Layer Fingerprinting and Attribution of Autonomous Web Agents
Dayeon Kang, Hyejun Jeong, Jade Sheffey +2
As AI web agents proliferate, combining large language models with autonomous, browser-level control, indiscriminate content scraping by web agents has emerged as a privacy and sec…
AI Snitches Get Glitches: Towards Evading Agentic Surveillance
Hyejun Jeong, Dzung Pham, Amir Houmansadr +1
AI agents are now routinely entrusted with access to users' data and communications, operating with growing autonomy and low human supervision. This increasing reliance on AI agent…
Throttling Web Agents Using Reasoning Gates
Abhinav Kumar, Jaechul Roh, Ali Naseh +2
AI web agents use Internet resources at far greater speed, scale, and complexity -- changing how users and services interact. Deployed maliciously or erroneously, these agents coul…
R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model
Ali Naseh, Harsh Chaudhari, Jaechul Roh +3
DeepSeek recently released R1, a high-performing large language model (LLM) optimized for reasoning tasks. Despite its efficient training pipeline, R1 achieves competitive performa…
Can Large Language Models Really Recognize Your Name?
Dzung Pham, Peter Kairouz, Niloofar Mireshghallah +3
Large language models (LLMs) are increasingly being used in privacy pipelines to detect and remedy sensitive data leakage. These solutions often rely on the premise that LLMs can r…
Multilingual and Multi-Accent Jailbreaking of Audio LLMs
Jaechul Roh, Virat Shejwalkar, Amir Houmansadr
Large Audio Language Models (LALMs) have significantly advanced audio understanding but introduce critical security risks, particularly through audio jailbreaks. While prior work h…
OverThink: Slowdown Attacks on Reasoning LLMs
Abhinav Kumar, Jaechul Roh, Ali Naseh +4
A reasoning language model (RLM) generates costly reasoning tokens, often hidden from the users, that help it excel at many tasks. Our Overthink attack targets RLM-based applicatio…
CensorLab: A Testbed for Censorship Experimentation
Jade Sheffey, Amir Houmansadr
Censorship and censorship circumvention are closely connected, and each is constantly making decisions in reaction to the other. When censors deploy a new Internet censorship techn…
ProxyGPT: Enabling User Anonymity in LLM Chatbots via (Un)Trustworthy Volunteer Proxies
Dzung Pham, Jade Sheffey, Chau Minh Pham +1
Popular large language model (LLM) chatbots such as ChatGPT and Claude require users to create an account with an email or a phone number before allowing full access to their servi…
Backdooring Bias () into Stable Diffusion Models
Ali Naseh, Jaechul Roh, Eugene Bagdasarian +1
Recent advances in large text-conditional diffusion models have revolutionized image generation by enabling users to create realistic, high-quality images from textual prompts, sig…
PostMark: A Robust Blackbox Watermark for Large Language Models
Yapei Chang, Kalpesh Krishna, Amir Houmansadr +2
The most effective techniques to detect LLM-generated text rely on inserting a detectable signature -- or watermark -- during the model's decoding process. Most existing watermarki…
OSLO: One-Shot Label-Only Membership Inference Attacks
Yuefeng Peng, Jaechul Roh, Subhransu Maji +1
We introduce One-Shot Label-Only (OSLO) membership inference attacks (MIAs), which accurately infer a given sample's membership in a target model's training set with high precision…
Iteratively Prompting Multimodal LLMs to Reproduce Natural and AI-Generated Images
Ali Naseh, Katherine Thai, Mohit Iyyer +1
With the digital imagery landscape rapidly evolving, image stocks and AI-generated image marketplaces have become central to visual media. Traditional stock images now exist alongs…
Understanding (Un)Intended Memorization in Text-to-Image Generative Models
Ali Naseh, Jaechul Roh, Amir Houmansadr
Multimodal machine learning, especially text-to-image models like Stable Diffusion and DALL-E 3, has gained significance for transforming text into detailed images. Despite their g…
Memory Triggers: Unveiling Memorization in Text-To-Image Generative Models through Word-Level Duplication
Ali Naseh, Jaechul Roh, Amir Houmansadr
Diffusion-based models, such as the Stable Diffusion model, have revolutionized text-to-image synthesis with their ability to produce high-quality, high-resolution images. These ad…
Diffence: Fencing Membership Privacy With Diffusion Models
Yuefeng Peng, Ali Naseh, Amir Houmansadr
Deep learning models, while achieving remarkable performances, are vulnerable to membership inference attacks (MIAs). Although various defenses have been proposed, there is still s…
RAIFLE: Reconstruction Attacks on Interaction-based Federated Learning with Adversarial Data Manipulation
Dzung Pham, Shreyas Kulkarni, Amir Houmansadr
Federated learning has emerged as a promising privacy-preserving solution for machine learning domains that rely on user interactions, particularly recommender systems and online l…
CensorSpoofer: Asymmetric Communication with IP Spoofing for Censorship-Resistant Web Browsing
Qiyan Wang, Xun Gong, Giang T. K. Nguyen +2
A key challenge in censorship-resistant web browsing is being able to direct legitimate users to redirection proxies while preventing censors, posing as insiders, from discovering…