197 citations · 299 across the 47 of their papers we have counts for
52 papers
SHIP: Structured and Hierarchical Insight with Privacy
Kai Chen, Guisi Ni, Albert Cheu +4
Extracting insights from textual data while protecting user privacy is increasingly important. Existing methods produce private insights in diverse forms for different analytical p…
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…
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…
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…
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~(…
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…
"It's like a pet...but my pet doesn't collect data about me": Multi-person Households' Privacy Design Preferences for Household Robots
Jennica Li, Shirley Zhang, Dakota Sullivan +4
Household robots boasting mobility, more sophisticated sensors, and powerful processing models have become increasingly prevalent in the commercial market. However, these features…
Prediction with Expert Advice under Local Differential Privacy
Ben Jacobsen, Kassem Fawaz
We study the classic problem of prediction with expert advice under the constraint of local differential privacy (LDP). In this context, we first show that a classical algorithm na…
Auto-SPT: Automating Semantic Preserving Transformations for Code
Ashish Hooda, Mihai Christodorescu, Chuangang Ren +3
Machine learning (ML) models for code clone detection determine whether two pieces of code are semantically equivalent, which in turn is a key building block for software-engineeri…
Personalizing Agent Privacy Decisions via Logical Entailment
James Flemings, Ren Yi, Octavian Suciu +3
Personal large language model (LLM) agents increasingly perform tasks that require access to user data, raising concerns about appropriate data disclosure. We show that relying sol…
Benchmarking LLM Privacy Recognition for Social Robot Decision Making
Dakota Sullivan, Shirley Zhang, Jennica Li +3
While robots have previously utilized rule-based systems or probabilistic models for user interaction, the rapid evolution of large language models (LLMs) presents new opportunitie…
What Really is a Member? Discrediting Membership Inference via Poisoning
Neal Mangaokar, Ashish Hooda, Zhuohang Li +5
Membership inference tests aim to determine whether a particular data point was included in a language model's training set. However, recent works have shown that such tests often…
Private Continual Counting of Unbounded Streams
Ben Jacobsen, Kassem Fawaz
We study the problem of differentially private continual counting in the unbounded setting where the input size is not known in advance. Current state-of-the-art algorithms bas…
Exploring Families' Use and Mediation of Generative AI: A Multi-User Perspective
Shirley Zhang, Dakota Sullivan, Jennica Li +4
Generative AI (GenAI) platforms, such as ChatGPT, have gained popularity among the public due to their ease of access, use, and support of educational and creative activities. Desp…
"Impressively Scary:" Exploring User Perceptions and Reactions to Unraveling Machine Learning Models in Social Media Applications
Jack West, Bengisu Cagiltay, Shirley Zhang +3
Machine learning models deployed locally on social media applications are used for features, such as face filters which read faces in-real time, and they expose sensitive attribute…
Automatically Detecting Online Deceptive Patterns
Asmit Nayak, Shirley Zhang, Yash Wani +2
Deceptive patterns in digital interfaces manipulate users into making unintended decisions, exploiting cognitive biases and psychological vulnerabilities. These patterns have becom…
Reliable Heading Tracking for Pedestrian Road Crossing Prediction Using Commodity Devices
Yucheng Yang, Jingjie Li, Kassem Fawaz
Pedestrian heading tracking enables applications in pedestrian navigation, traffic safety, and accessibility. Previous works, using inertial sensor fusion or machine learning, are…
Evaluating the Impact of Warning Modalities and False Alarms in Pedestrian Crossing Alert System
Hesham Alyamani, Yucheng Yang, David Noyce +2
With the steadily increasing pedestrian fatalities, pedestrian safety is a growing concern, especially in urban environments. Advanced Driver Assistance Systems (ADAS) have been de…
PolicyLR: A Logic Representation For Privacy Policies
Ashish Hooda, Rishabh Khandelwal, Prasad Chalasani +2
Privacy policies are crucial in the online ecosystem, defining how services handle user data and adhere to regulations such as GDPR and CCPA. However, their complexity and frequent…
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…
A Picture is Worth 500 Labels: A Case Study of Demographic Disparities in Local Machine Learning Models for Instagram and TikTok
Jack West, Lea Thiemt, Shimaa Ahmed +3
Mobile apps have embraced user privacy by moving their data processing to the user's smartphone. Advanced machine learning (ML) models, such as vision models, can now locally analy…
PRP: Propagating Universal Perturbations to Attack Large Language Model Guard-Rails
Neal Mangaokar, Ashish Hooda, Jihye Choi +4
Large language models (LLMs) are typically aligned to be harmless to humans. Unfortunately, recent work has shown that such models are susceptible to automated jailbreak attacks th…
I see an IC: A Mixed-Methods Approach to Study Human Problem-Solving Processes in Hardware Reverse Engineering
René Walendy, Markus Weber, Jingjie Li +7
Trust in digital systems depends on secure hardware, often assured through Hardware Reverse Engineering (HRE). This work develops methods for investigating human problem-solving pr…
Do Large Code Models Understand Programming Concepts? Counterfactual Analysis for Code Predicates
Ashish Hooda, Mihai Christodorescu, Miltiadis Allamanis +3
Large Language Models' success on text generation has also made them better at code generation and coding tasks. While a lot of work has demonstrated their remarkable performance o…