3 papers
cs.CR2026
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…
cs.CR2025
Real AI Agents with Fake Memories: Fatal Context Manipulation Attacks on Web3 Agents
Atharv Singh Patlan, Peiyao Sheng, S. Ashwin Hebbar +2
AI agents integrated with Web3 offer autonomy and openness but raise security concerns as they interact with financial protocols and immutable smart contracts. This paper investiga…
cs.CR2025
Context manipulation attacks : Web agents are susceptible to corrupted memory
Atharv Singh Patlan, Ashwin Hebbar, Pramod Viswanath +1
Autonomous web navigation agents, which translate natural language instructions into sequences of browser actions, are increasingly deployed for complex tasks across e-commerce, in…