382 citations · 2.5k across the 96 of their papers we have counts for
47 papers · 1 filter
BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
Tinghao Xie, Xiangyu Qi, Ping He +3
We present a novel defense, against backdoor attacks on Deep Neural Networks (DNNs), wherein adversaries covertly implant malicious behaviors (backdoors) into DNNs. Our defense fal…
Visual Adversarial Examples Jailbreak Aligned Large Language Models
Xiangyu Qi, Kaixuan Huang, Ashwinee Panda +3
Recently, there has been a surge of interest in integrating vision into Large Language Models (LLMs), exemplified by Visual Language Models (VLMs) such as Flamingo and GPT-4. This…
A Randomized Approach for Tight Privacy Accounting
Jiachen T. Wang, Saeed Mahloujifar, Tong Wu +2
Bounding privacy leakage over compositions, i.e., privacy accounting, is a key challenge in differential privacy (DP). The privacy parameter ($\eps$ or ) is often easy to estima…
QUICstep: Evaluating connection migration based QUIC censorship circumvention
Seungju Lee, Mona Wang, Watson Jia +4
Internet censors often rely on information in the first few packets of a connection to censor unwanted traffic. With the rise of the QUIC transport protocol, prior work has suggest…
How Effective is Multiple-Vantage-Point Domain Control Validation?
Grace Cimaszewski, Henry Birge-Lee, Liang Wang +2
Multiple-vantage-point domain control validation (multiVA) is an emerging defense for mitigating BGP hijacking attacks against certificate authorities. While the adoption of multiV…
Renyi Differential Privacy of Propose-Test-Release and Applications to Private and Robust Machine Learning
Jiachen T. Wang, Saeed Mahloujifar, Shouda Wang +2
Propose-Test-Release (PTR) is a differential privacy framework that works with local sensitivity of functions, instead of their global sensitivity. This framework is typically used…