6 citations · 12 across the 10 of their papers we have counts for
10 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 LLM 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 Agentic Systems
Nils Palumbo, Sarthak Choudhary, Jihye Choi +4
As agentic computing systems grow increasingly popular, they raise serious security concerns due to their susceptibility to various attacks. While prior research efforts aim to mit…
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…
MALADE: Orchestration of LLM-powered Agents with Retrieval Augmented Generation for Pharmacovigilance
Jihye Choi, Nils Palumbo, Prasad Chalasani +4
In the era of Large Language Models (LLMs), given their remarkable text understanding and generation abilities, there is an unprecedented opportunity to develop new, LLM-based meth…
Validating Mechanistic Interpretations: An Axiomatic Approach
Nils Palumbo, Ravi Mangal, Zifan Wang +3
Mechanistic interpretability aims to reverse engineer the computation performed by a neural network in terms of its internal components. Although there is a growing body of researc…
Two Heads are Actually Better than One: Towards Better Adversarial Robustness via Transduction and Rejection
Nils Palumbo, Yang Guo, Xi Wu +3
Both transduction and rejection have emerged as important techniques for defending against adversarial perturbations. A recent work by Goldwasser et al. showed that rejection combi…
On Robust Mean Estimation under Coordinate-level Corruption
Zifan Liu, Jongho Park, Theodoros Rekatsinas +1
We study the problem of robust mean estimation and introduce a novel Hamming distance-based measure of distribution shift for coordinate-level corruptions. We show that this measur…