6 citations · 10 across the 9 of their papers we have counts for
6 papers · 1 filter
Cascade: Composing Software-Hardware Attack Gadgets for Adversarial Threat Amplification in Compound AI Systems
Sarbartha Banerjee, Prateek Sahu, Anjo Vahldiek-Oberwagner +2
Rapid progress in generative AI has given rise to Compound AI systems - pipelines comprised of multiple large language models (LLM), software tools and database systems. Compound A…
SoK: A Systems Perspective on Compound AI Threats and Countermeasures
Sarbartha Banerjee, Prateek Sahu, Mulong Luo +3
Large language models (LLMs) used across enterprises often use proprietary models and operate on sensitive inputs and data. The wide range of attack vectors identified in prior res…
Obsidian: Cooperative State-Space Exploration for Performant Inference on Secure ML Accelerators
Sarbartha Banerjee, Shijia Wei, Prakash Ramrakhyani +1
Trusted execution environments (TEEs) for machine learning accelerators are indispensable in secure and efficient ML inference. Optimizing workloads through state-space exploration…
ConfusedPilot: Confused Deputy Risks in RAG-based LLMs
Ayush RoyChowdhury, Mulong Luo, Prateek Sahu +2
Retrieval augmented generation (RAG) is a process where a large language model (LLM) retrieves useful information from a database and then generates the responses. It is becoming p…
Bandwidth Utilization Side-Channel on ML Inference Accelerators
Sarbartha Banerjee, Shijia Wei, Prakash Ramrakhyani +1
Accelerators used for machine learning (ML) inference provide great performance benefits over CPUs. Securing confidential model in inference against off-chip side-channel attacks i…
SESAME: Software defined Enclaves to Secure Inference Accelerators with Multi-tenant Execution
Sarbartha Banerjee, Prakash Ramrakhyani, Shijia Wei +1
Hardware-enclaves that target complex CPU designs compromise both security and performance. Programs have little control over micro-architecture, which leads to side-channel leaks,…