ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Shiqing Ma

Shiqing Ma

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, 3:09 AM AMS

17

papers

425

total citations

papers (17)

BppAttack: Stealthy and Efficient Trojan Attacks Against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning

Detecting Backdoors in Pre-Trained Encoders

Training with More Confidence: Mitigating Injected and Natural Backdoors During Training

NEURIPS 2022arXiv

Rethinking the Reverse-engineering of Trojan Triggers

NEURIPS 2022arXiv

Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift

How to Trace Latent Generative Model Generated Images without Artificial Watermark?

MLLM-as-a-Judge for Image Safety without Human Labeling

LOTUS: Evasive and Resilient Backdoor Attacks through Sub-Partitioning

Invisible Backdoor Attack against Self-supervised Learning

Continuous Concepts Removal in Text-to-image Diffusion Models

NEURIPS 2025arXiv

Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zone

Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximation

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening

Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration

Complex Backdoor Detection by Symmetric Feature Differencing

Better Trigger Inversion Optimization in Backdoor Scanning

Where Did I Come From? Origin Attribution of AI-Generated Images