ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Shengshan Hu

Shengshan Hu

Topic trends: 32,543 papers · similarity ≥ 0.4 · year ≥ 2024 · Data sourced from Semantic Scholar

34,598 papers | Abstracts: 31,650 (91.5%) | Citations: 34,598 (100.0%) | arXiv: 26,074 (75.4%)

Built: Feb 15, 2026, 4:51 AM AMS

14

papers

316

total citations

papers (14)

Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-Robust Makeup Transfer

Detecting Backdoors During the Inference Stage Based on Corruption Robustness Consistency

Downstream-agnostic Adversarial Examples

NumbOD: A Spatial-Frequency Fusion Attack Against Object Detectors

Breaking Barriers in Physical-World Adversarial Examples: Improving Robustness and Transferability via Robust Feature

Test-Time Backdoor Detection for Object Detection Models

Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2

NEURIPS 2025arXiv

Revisiting Gradient Pruning: A Dual Realization for Defending against Gradient Attacks

Benchmarking and Analyzing Robust Point Cloud Recognition: Bag of Tricks for Defending Adversarial Examples

BadRobot: Jailbreaking Embodied LLM Agents in the Physical World

Improving Generalization of Universal Adversarial Perturbation via Dynamic Maximin Optimization

Towards Model Extraction Attacks in GAN-Based Image Translation via Domain Shift Mitigation

MARS: A Malignity-Aware Backdoor Defense in Federated Learning

NEURIPS 2025arXiv

Detecting and Corrupting Convolution-based Unlearnable Examples