3 citations · 10 across the 15 of their papers we have counts for
18 papers
Localize-and-Detect: Auditing Task-Level Poisoning in Instruction-Tuned Models
Luze Sun, Cristina Nita-Rotaru, Alina Oprea
Instruction fine-tuning adapts a pretrained language model to follow instructions by training it on instruction--response pairs from a collection of tasks, such as summarization an…
PoisonForge: Task-Level Targeted Poisoning Benchmark for Instruction-Tuned LLMs
Luze Sun, Anshuman Suri, Harsh Chaudhari +2
When practitioners fine-tune LLMs on unvetted datasets, an adversary can exploit the data supply chain through task-level poisoning: inserting a small number of crafted instruction…
APWA: A Distributed Architecture for Parallelizable Agentic Workflows
Evan Rose, Tushin Mallick, Matthew D. Laws +2
Autonomous multi-agent systems based on large language models (LLMs) have demonstrated remarkable abilities in independently solving complex tasks in a wide breadth of application…
Thought-Transfer: Indirect Targeted Poisoning Attacks on Chain-of-Thought Reasoning Models
Harsh Chaudhari, Ethan Rathbun, Hanna Foerster +5
Chain-of-Thought (CoT) reasoning has emerged as a powerful technique for enhancing large language models' capabilities by generating intermediate reasoning steps for complex tasks.…
Identifying Models Behind Text-to-Image Leaderboards
Ali Naseh, Yuefeng Peng, Anshuman Suri +3
Text-to-image (T2I) models are increasingly popular, producing a large share of AI-generated images online. To compare model quality, voting-based leaderboards have become the stan…
Text-to-Image Models Leave Identifiable Signatures: Implications for Leaderboard Security
Ali Naseh, Anshuman Suri, Yuefeng Peng +3
Generative AI leaderboards are central to evaluating model capabilities, but remain vulnerable to manipulation. Among key adversarial objectives is rank manipulation, where an atta…
Exploiting Leaderboards for Large-Scale Distribution of Malicious Models
Anshuman Suri, Harsh Chaudhari, Yuefeng Peng +3
While poisoning attacks on machine learning models have been extensively studied, the mechanisms by which adversaries can distribute poisoned models at scale remain largely unexplo…
Black-Box Privacy Attacks on Shared Representations in Multitask Learning
John Abascal, Nicolás Berrios, Alina Oprea +3
Multitask learning (MTL) has emerged as a powerful paradigm that leverages similarities among multiple learning tasks, each with insufficient samples to train a standalone model, t…
Toward Principled LLM Safety Testing: Solving the Jailbreak Oracle Problem
Shuyi Lin, Anshuman Suri, Alina Oprea +1
As large language models (LLMs) become increasingly deployed in safety-critical applications, the lack of systematic methods to assess their vulnerability to jailbreak attacks pres…
R1dacted: Investigating Local Censorship in DeepSeek's R1 Language Model
Ali Naseh, Harsh Chaudhari, Jaechul Roh +3
DeepSeek recently released R1, a high-performing large language model (LLM) optimized for reasoning tasks. Despite its efficient training pipeline, R1 achieves competitive performa…
Cascading Adversarial Bias from Injection to Distillation in Language Models
Harsh Chaudhari, Jamie Hayes, Matthew Jagielski +3
Model distillation has become essential for creating smaller, deployable language models that retain larger system capabilities. However, widespread deployment raises concerns abou…
SAGA: A Security Architecture for Governing AI Agentic Systems
Georgios Syros, Anshuman Suri, Jacob Ginesin +2
Large Language Model (LLM)-based agents increasingly interact, collaborate, and delegate tasks to one another autonomously with minimal human interaction. Industry guidelines for a…
ACE: A Security Architecture for LLM-Integrated App Systems
Evan Li, Tushin Mallick, Evan Rose +3
LLM-integrated app systems extend the utility of Large Language Models (LLMs) with third-party apps that are invoked by a system LLM using interleaved planning and execution phases…
DROP: Poison Dilution via Knowledge Distillation for Federated Learning
Georgios Syros, Anshuman Suri, Farinaz Koushanfar +2
Federated Learning is vulnerable to adversarial manipulation, where malicious clients can inject poisoned updates to influence the global model's behavior. While existing defense m…
Riddle Me This! Stealthy Membership Inference for Retrieval-Augmented Generation
Ali Naseh, Yuefeng Peng, Anshuman Suri +3
Retrieval-Augmented Generation (RAG) enables Large Language Models (LLMs) to generate grounded responses by leveraging external knowledge databases without altering model parameter…
UTrace: Poisoning Forensics for Private Collaborative Learning
Evan Rose, Hidde Lycklama, Harsh Chaudhari +3
Privacy-preserving machine learning (PPML) systems enable multiple data owners to collaboratively train models without revealing their raw, sensitive data by leveraging cryptograph…
Phantom: General Backdoor Attacks on Retrieval Augmented Language Generation
Harsh Chaudhari, Giorgio Severi, John Abascal +6
Retrieval Augmented Generation (RAG) expands the capabilities of modern large language models (LLMs), by anchoring, adapting, and personalizing their responses to the most relevant…
Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning
Harsh Chaudhari, Giorgio Severi, Alina Oprea +1
The integration of machine learning (ML) in numerous critical applications introduces a range of privacy concerns for individuals who provide their datasets for model training. One…