280 citations · 1.4k across the 75 of their papers we have counts for
11 papers · 1 filter
VeriGuard: Enhancing LLM Agent Safety via Verified Code Generation
Lesly Miculicich, Mihir Parmar, Hamid Palangi +4
The deployment of autonomous AI agents in sensitive domains, such as healthcare, introduces critical risks to safety, security, and privacy. These agents may deviate from user obje…
Indirect Prompt Injections: Are Firewalls All You Need, or Stronger Benchmarks?
Rishika Bhagwatkar, Kevin Kasa, Abhay Puri +5
AI agents are vulnerable to indirect prompt injection attacks, where malicious instructions embedded in external content or tool outputs cause unintended or harmful behavior. Inspi…
Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain
Léo Boisvert, Abhay Puri, Chandra Kiran Reddy Evuru +7
While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the a…
Adaptive Diffusion Denoised Smoothing : Certified Robustness via Randomized Smoothing with Differentially Private Guided Denoising Diffusion
Frederick Shpilevskiy, Saiyue Lyu, Krishnamurthy Dj Dvijotham +2
We propose Adaptive Diffusion Denoised Smoothing, a method for certifying the predictions of a vision model against adversarial examples, while adapting to the input. Our key insig…
Correlated Noise Mechanisms for Differentially Private Learning
Krishna Pillutla, Jalaj Upadhyay, Christopher A. Choquette-Choo +9
This monograph explores the design and analysis of correlated noise mechanisms for differential privacy (DP), focusing on their application to private training of AI and machine le…
Through the Stealth Lens: Attention-Aware Defenses Against Poisoning in RAG
Sarthak Choudhary, Nils Palumbo, Ashish Hooda +2
Retrieval-augmented generation (RAG) systems are vulnerable to attacks that inject poisoned passages into the retrieved context, even at low corruption rates. We show that existing…
DoomArena: A framework for Testing AI Agents Against Evolving Security Threats
Leo Boisvert, Mihir Bansal, Chandra Kiran Reddy Evuru +9
We present DoomArena, a security evaluation framework for AI agents. DoomArena is designed on three principles: 1) It is a plug-in framework and integrates easily into realistic ag…
Large Language Models Can Verbatim Reproduce Long Malicious Sequences
Sharon Lin, Krishnamurthy, Dvijotham +4
Backdoor attacks on machine learning models have been extensively studied, primarily within the computer vision domain. Originally, these attacks manipulated classifiers to generat…
Keeping up with dynamic attackers: Certifying robustness to adaptive online data poisoning
Avinandan Bose, Laurent Lessard, Maryam Fazel +1
The rise of foundation models fine-tuned on human feedback from potentially untrusted users has increased the risk of adversarial data poisoning, necessitating the study of robustn…
No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms
Joshua Kazdan, Abhay Puri, Rylan Schaeffer +5
Leading language model (LM) providers like OpenAI and Anthropic allow customers to fine-tune frontier LMs for specific use cases. To prevent abuse, these providers apply filters to…
Norm-Bounded Low-Rank Adaptation
Ruigang Wang, Krishnamurthy Dvijotham, Ian R. Manchester
In this work, we propose norm-bounded low-rank adaptation (NB-LoRA) for parameter-efficient fine tuning. NB-LoRA is a novel parameterization of low-rank weight adaptations that adm…