18 papers
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…
WebSP-Eval: Evaluating Web Agents on Website Security and Privacy Tasks
Guruprasad Viswanathan Ramesh, Asmit Nayak, Basieem Siddique +1
Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate general-purpose performance~(…
CounterFace: A Synthetic Face Dataset for Fine-Grained Counterfactual Evaluation of Face Recognition Systems
Guruprasad Viswanathan Ramesh, Ashish Hooda, Shimaa Ahmed +3
Face recognition (FR) systems are widely deployed in critical applications, making their reliability and robustness across diverse populations and conditions essential. Standard ev…
Optimal Rates for Differentially Private Hypothesis Testing with E-values
Ben Jacobsen, Tomas Gonzalez, Gavin Brown +2
E-values have attracted considerable interest in recent years as flexible tools for enabling anytime-valid and adaptive data analysis. Hypothesis testing is at the core of many of…
Text-Based Personas for Simulating User Privacy Decisions
Kassem Fawaz, Ren Yi, Octavian Suciu +4
The ability to simulate human privacy decisions has significant implications for aligning autonomous agents with individual intent and conducting cost-effective, large-scale privac…
Challenges and Future Directions in Agentic Reverse Engineering Systems
Salem Radey, Jack West, Kassem Fawaz
Agentic systems built on large language models (LLMs) are increasingly being used for complex security tasks, including binary reverse engineering (RE). Despite recent growth in po…