collaborators

5 papers

cs.SE2025

WITNESS: A lightweight and practical approach to fine-grained predictive mutation testing

Zeyu Lu, Peng Zhang, Chun Yong Chong +5

Existing fine-grained predictive mutation testing studies predominantly rely on deep learning, which faces two critical limitations in practice: (1) Exorbitant computational costs.…

cs.CR2025

Backdoor Attacks and Defenses in Computer Vision Domain: A Survey

Bilal Hussain Abbasi, Yanjun Zhang, Leo Zhang +1

Backdoor (trojan) attacks embed hidden, controllable behaviors into machine-learning models so that models behave normally on benign inputs but produce attacker-chosen outputs when…

cs.CR2025

ConSeg: Contextual Backdoor Attack Against Semantic Segmentation

Bilal Hussain Abbasi, Zirui Gong, Yanjun Zhang +3

Despite significant advancements in computer vision, semantic segmentation models may be susceptible to backdoor attacks. These attacks, involving hidden triggers, aim to cause the…

cs.LG2025

Stability and List-Replicability for Agnostic Learners

Ari Blondal, Shan Gao, Hamed Hatami +1

Two seminal papers--Alon, Livni, Malliaris, Moran (STOC 2019) and Bun, Livni, and Moran (FOCS 2020)--established the equivalence between online learnability and globally stable PAC…

cs.CV2025

Self-Attention-Based Contextual Modulation Improves Neural System Identification

Isaac Lin, Tianye Wang, Shang Gao +2

Convolutional neural networks (CNNs) have been shown to be state-of-the-art models for visual cortical neurons. Cortical neurons in the primary visual cortex are sensitive to conte…