6 papers
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…
Dependency-Aware Privacy for Multi-turn Agents
Divyam Anshumaan, Sarthak Choudhary, Nils Palumbo +1
LLM agents release private data across multi-service interactions. Existing prompt sanitizers based on metric differential privacy treat each release independently, so adversaries…
Formal Policy Enforcement for Real-World Agentic Systems
Nils Palumbo, Sarthak Choudhary, Jihye Choi +3
Security policy enforcement in contemporary agentic systems predominantly consists of embedding natural-language policies within an agent's system prompt and delegating compliance…
How Not to Detect Prompt Injections with an LLM
Sarthak Choudhary, Divyam Anshumaan, Nils Palumbo +1
LLM-integrated applications and agents are vulnerable to prompt injection attacks, where adversaries embed malicious instructions within seemingly benign input data to manipulate t…
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…