17 citations · 24 across the 11 of their papers we have counts for
12 papers
ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning
Zhengyue Zhao, Yingzi Ma, Somesh Jha +3
Large Language Models have shown impressive generative capabilities across diverse tasks, but their safety remains a critical concern. Existing post-training alignment methods, suc…
What Really is a Member? Discrediting Membership Inference via Poisoning
Neal Mangaokar, Ashish Hooda, Zhuohang Li +5
Membership inference tests aim to determine whether a particular data point was included in a language model's training set. However, recent works have shown that such tests often…
AutoDAN-Turbo: A Lifelong Agent for Strategy Self-Exploration to Jailbreak LLMs
Xiaogeng Liu, Peiran Li, Edward Suh +7
In this paper, we propose AutoDAN-Turbo, a black-box jailbreak method that can automatically discover as many jailbreak strategies as possible from scratch, without any human inter…
Functional Homotopy: Smoothing Discrete Optimization via Continuous Parameters for LLM Jailbreak Attacks
Zi Wang, Divyam Anshumaan, Ashish Hooda +2
Optimization methods are widely employed in deep learning to identify and mitigate undesired model responses. While gradient-based techniques have proven effective for image models…
A New Era in LLM Security: Exploring Security Concerns in Real-World LLM-based Systems
Fangzhou Wu, Ning Zhang, Somesh Jha +2
Large Language Model (LLM) systems are inherently compositional, with individual LLM serving as the core foundation with additional layers of objects such as plugins, sandbox, and…
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
Neal Mangaokar, Ashish Hooda, Jihye Choi +4
Large language models (LLMs) are typically aligned to be harmless to humans. Unfortunately, recent work has shown that such models are susceptible to automated jailbreak attacks th…
Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates
Ashish Hooda, Mihai Christodorescu, Miltiadis Allamanis +3
Large Language Models' success on text generation has also made them better at code generation and coding tasks. While a lot of work has demonstrated their remarkable performance o…
A Somewhat Robust Image Watermark against Diffusion-based Editing Models
Mingtian Tan, Tianhao Wang, Somesh Jha
Recently, diffusion models (DMs) have become the state-of-the-art method for image synthesis. Editing models based on DMs, known for their high fidelity and precision, have inadver…
slash: A Technique for Static Configuration-Logic Identification
Mohannad Alhanahnah, Philipp Schubert, Thomas Reps +2
Researchers have recently devised tools for debloating software and detecting configuration errors. Several of these tools rely on the observation that programs are composed of an…
Adaptation with Self-Evaluation to Improve Selective Prediction in LLMs
Jiefeng Chen, Jinsung Yoon, Sayna Ebrahimi +3
Large language models (LLMs) have recently shown great advances in a variety of tasks, including natural language understanding and generation. However, their use in high-stakes de…
Robust and Actively Secure Serverless Collaborative Learning
Olive Franzese, Adam Dziedzic, Christopher A. Choquette-Choo +7
Collaborative machine learning (ML) is widely used to enable institutions to learn better models from distributed data. While collaborative approaches to learning intuitively prote…
Why Train More? Effective and Efficient Membership Inference via Memorization
Jihye Choi, Shruti Tople, Varun Chandrasekaran +1
Membership Inference Attacks (MIAs) aim to identify specific data samples within the private training dataset of machine learning models, leading to serious privacy violations and…