ResearchAlpha Leak

Conferences Topics Top Authors Rankings Browse All

Home/Authors/Aishan Liu

Aishan Liu

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, 3:11 AM AMS

15

papers

453

total citations

papers (15)

Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical World

BadCLIP: Dual-Embedding Guided Backdoor Attack on Multimodal Contrastive Learning

Defensive Patches for Robust Recognition in the Physical World

Revisiting Backdoor Attacks against Large Vision-Language Models from Domain Shift

Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks

T2V-OptJail: Discrete Prompt Optimization for Text-to-Video Jailbreak Attacks

NEURIPS 2025arXiv

Bias-based Universal Adversarial Patch Attack for Automatic Check-out

Lie Detector: Unified Backdoor Detection via Cross-Examination Framework

NEURIPS 2025arXiv

Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing

NEURIPS 2025arXiv

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks

CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement Attacks

Exploring Endogenous Shift for Cross-Domain Detection: A Large-Scale Benchmark and Perturbation Suppression Network

Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization

Exploring Semantic-constrained Adversarial Example with Instruction Uncertainty Reduction

NEURIPS 2025arXiv

Spatiotemporal Attacks for Embodied Agents