3 citations · 3 across the 9 of their papers we have counts for
14 papers
Kerkoporta: Injecting Structured-Output Backdoors in Reasoning Coding Agents
Georgios Syros, Blake Bullwinkel, Alina Oprea +4
Existing large language model (LLM) backdoor attacks operate primarily in chat settings, where the risk is bounded by free-form text outputs. AI agents remove that bound by perform…
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…
PANDA: A Decentralized Architecture with Flexible Orchestration for Scalable, Fault-Tolerant Multi-Agent Systems
Matthew D. Laws, Cristina Nita-Rotaru
Existing architectures for LLM-based multi-agent systems (MAS) cannot reliably and efficiently solve multi-step tasks at scale: they struggle to support large numbers of agents and…
Beyond Predictable Paths: Redefining AI Security Incident Reporting for Agents
Anastasia Pustozerova, Eugene Bagdasarian, Luca Beurer-Kellner +22
AI agents are being deployed rapidly, accompanied by a growing number of AI-specific attacks and corresponding incidents. As incident reporting becomes increasingly important for l…
ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments
Zixuan Wu, Cristina Nita-Rotaru
Large language models are increasingly deployed for security-sensitive tasks such as vulnerability detection and code review. Their reliance on natural-language context embedded in…
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…
MAGIQ: A Post-Quantum Multi-Agentic AI Governance System with Provable Security
Sepideh Avizheh, Tushin Mallick, Alina Oprea +2
Our computing ecosystem is being transformed by two emerging paradigms: the increased deployment of agentic AI systems and advancements in quantum computing. With respect to agenti…
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…
Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries
Matthew D. Laws, Alina Oprea, Cristina Nita-Rotaru
Agentic AI governance is a critical component of agentic AI infrastructure ensuring that agents follow their owner's communication and interaction policies, and providing protectio…
MUZZLE: Adaptive Agentic Red-Teaming of Web Agents Against Indirect Prompt Injection Attacks
Georgios Syros, Evan Rose, Brian Grinstead +4
Large language model (LLM) based web agents are increasingly deployed to automate complex online tasks by directly interacting with web sites and performing actions on users' behal…
Quantum Disruption: An SOK of How Post-Quantum Attackers Reshape Blockchain Security and Performance
Tushin Mallick, Maya Zeldin, Murat Cenk +1
As quantum computing advances, classical cryptographic systems - signature schemes, key exchange protocols, public-key encryption, and certain hash constructions - that secure most…
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…
Classifying Implementations of Cryptographic Primitives and Protocols that Use Post-Quantum Algorithms
Tushin Mallick, Cristina Nita-Rotaru, Ashish Kundu +1
Classification techniques can be used to analyze system behaviors, network protocols, and cryptographic primitives based on identifiable traits. While useful for defense, such clas…