15 citations · 32 across the 17 of their papers we have counts for
10 papers · 1 filter
Agent Security is a Systems Problem
Mihai Christodorescu, Earlence Fernandes, Ashish Hooda +11
We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants…
Undetectable Backdoors in Model Parameters: Hiding Sparse Secrets in High Dimensions
Sarthak Choudhary, Atharv Singh Patlan, Nils Palumbo +3
We present Sparse Backdoor, a supply-chain attack that plants a provably undetectable backdoor in pre-trained image classifiers, including convolutional networks and Vision Transfo…
Systems Security Foundations for Agentic Computing
Mihai Christodorescu, Earlence Fernandes, Ashish Hooda +11
In recent years, agentic artificial intelligence (AI) systems are becoming increasingly widespread. These systems allow agents to use various tools, such as web browsers, compilers…
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…
Fun-tuning: Characterizing the Vulnerability of Proprietary LLMs to Optimization-based Prompt Injection Attacks via the Fine-Tuning Interface
Andrey Labunets, Nishit V. Pandya, Ashish Hooda +2
We surface a new threat to closed-weight Large Language Models (LLMs) that enables an attacker to compute optimization-based prompt injections. Specifically, we characterize how an…
PolicyLR: A Logic Representation For Privacy Policies
Ashish Hooda, Rishabh Khandelwal, Prasad Chalasani +2
Privacy policies are crucial in the online ecosystem, defining how services handle user data and adhere to regulations such as GDPR and CCPA. However, their complexity and frequent…
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…
Stateful Defenses for Machine Learning Models Are Not Yet Secure Against Black-box Attacks
Ryan Feng, Ashish Hooda, Neal Mangaokar +3
Recent work has proposed stateful defense models (SDMs) as a compelling strategy to defend against a black-box attacker who only has query access to the model, as is common for onl…
SkillFence: A Systems Approach to Practically Mitigating Voice-Based Confusion Attacks
Ashish Hooda, Matthew Wallace, Kushal Jhunjhunwalla +2
Voice assistants are deployed widely and provide useful functionality. However, recent work has shown that commercial systems like Amazon Alexa and Google Home are vulnerable to vo…
Re-purposing Perceptual Hashing based Client Side Scanning for Physical Surveillance
Ashish Hooda, Andrey Labunets, Tadayoshi Kohno +1
Content scanning systems employ perceptual hashing algorithms to scan user content for illegal material, such as child pornography or terrorist recruitment flyers. Perceptual hashi…