Siyuan Liang

Orcid: 0000-0002-6154-0233

Affiliations:

National University of Singapore, School of Computer of Science, Singapore
Chinese Academy of Sciences, Institute of Information Engineering, Beijing, China (former)

According to our database¹, Siyuan Liang authored at least 111 papers between 2018 and 2026.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book In proceedings Article PhD thesis Dataset Other

Bibliography

2026

T2VShield: Model-Agnostic Jailbreak Defense for Text-to-Video Models.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., April, 2026

R-PGA: Robust Physical Adversarial Camouflage Generation via Relightable 3D Gaussian Splatting.

[BibT_eX]

[DOI]

CoRR, March, 2026

CtrlAttack: A Unified Attack on World-Model Control in Diffusion Models.

[BibT_eX]

[DOI]

CoRR, March, 2026

When World Models Dream Wrong: Physical-Conditioned Adversarial Attacks against World Models.

[BibT_eX]

[DOI]

CoRR, February, 2026

BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning.

[BibT_eX]

[DOI]

CoRR, February, 2026

SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., January, 2026

Towards Reliable Medical LLMs: Benchmarking and Enhancing Confidence Estimation of Large Language Models in Medical Consultation.

[BibT_eX]

[DOI]

CoRR, January, 2026

TrapFlow: Controllable Website Fingerprinting Defense via Dynamic Backdoor Learning.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2026

CogMorph: Cognitive Morphing Attacks for Text-to-Image Models.

[BibT_eX]

[DOI]

IEEE Trans. Dependable Secur. Comput., 2026

WFCAT: Augmenting Website Fingerprinting With Channel-Wise Attention on Timing Features.

[BibT_eX]

[DOI]

IEEE Trans. Dependable Secur. Comput., 2026

SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

Adversarial Generation and Collaborative Evolution of Safety-Critical Scenarios for Autonomous Vehicles.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

GenderBias-VL: Benchmarking Gender Bias in Vision Language Models via Counterfactual Probing.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., December, 2025

Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing.

[BibT_eX]

[DOI]

CoRR, October, 2025

Review of Hallucination Understanding in Large Language and Vision Models.

[BibT_eX]

[DOI]

Zheng Yi Ho

Siyuan Liang

Dacheng Tao

CoRR, October, 2025

An Intelligent Badminton Handle With Multinode MEMS Sensors for Explainable Motion Recognition.

[BibT_eX]

[DOI]

IEEE Internet Things J., September, 2025

Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation.

[BibT_eX]

[DOI]

CoRR, September, 2025

Explaining multimodal LLMs via intra-modal token interactions.

[BibT_eX]

[DOI]

CoRR, September, 2025

Text Adversarial Attacks with Dynamic Outputs.

[BibT_eX]

[DOI]

CoRR, September, 2025

RoboView-Bias: Benchmarking Visual Bias in Embodied Agents for Robotic Manipulation.

[BibT_eX]

[DOI]

CoRR, September, 2025

SafeSteer: Adaptive Subspace Steering for Efficient Jailbreak Defense in Vision-Language Models.

[BibT_eX]

[DOI]

CoRR, September, 2025

FERD: Fairness-Enhanced Data-Free Robustness Distillation.

[BibT_eX]

[DOI]

CoRR, September, 2025

Universal Camouflage Attack on Vision-Language Models for Autonomous Driving.

[BibT_eX]

[DOI]

CoRR, September, 2025

SMA: Who Said That? Auditing Membership Leakage in Semi-Black-box RAG Controlling.

[BibT_eX]

[DOI]

CoRR, August, 2025

Bench2ADVLM: A Closed-Loop Benchmark for Vision-language Models in Autonomous Driving.

[BibT_eX]

[DOI]

CoRR, August, 2025

PromptSafe: Gated Prompt Tuning for Safe Text-to-Image Generation.

[BibT_eX]

[DOI]

CoRR, August, 2025

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., July, 2025

SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents.

[BibT_eX]

[DOI]

CoRR, July, 2025

Pre-trained Trojan Attacks for Visual Recognition.

[BibT_eX]

[DOI]

Int. J. Comput. Vis., June, 2025

AGENTSAFE: Benchmarking the Safety of Embodied Agents on Hazardous Instructions.

[BibT_eX]

[DOI]

CoRR, June, 2025

Screen Hijack: Visual Poisoning of VLM Agents in Mobile Environments.

[BibT_eX]

[DOI]

CoRR, June, 2025

Pushing the Limits of Safety: A Technical Report on the ATLAS Challenge 2025.

[BibT_eX]

[DOI]

CoRR, June, 2025

Robust Anti-Backdoor Instruction Tuning in LVLMs.

[BibT_eX]

[DOI]

CoRR, June, 2025

SRD: Reinforcement-Learned Semantic Perturbation for Backdoor Defense in VLMs.

[BibT_eX]

[DOI]

CoRR, June, 2025

No Query, No Access.

[BibT_eX]

[DOI]

CoRR, May, 2025

Jailbreaking the Text-to-Video Generative Models.

[BibT_eX]

[DOI]

CoRR, May, 2025

Natural Reflection Backdoor Attack on Vision Language Model for Autonomous Driving.

[BibT_eX]

[DOI]

CoRR, May, 2025

Less is More: Efficient Black-box Attribution via Minimal Interpretable Subset Selection.

[BibT_eX]

[DOI]

CoRR, April, 2025

Lie Detector: Unified Backdoor Detection via Cross-Examination Framework.

[BibT_eX]

[DOI]

CoRR, March, 2025

Adversarial Training for Multimodal Large Language Models against Jailbreak Attacks.

[BibT_eX]

[DOI]

CoRR, March, 2025

Black-Box Adversarial Attack on Vision Language Models for Autonomous Driving.

[BibT_eX]

[DOI]

CoRR, January, 2025

CogMorph: Cognitive Morphing Attacks for Text-to-Image Models.

[BibT_eX]

[DOI]

CoRR, January, 2025

Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2025

CleanerCLIP: Fine-Grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2025

Compromising LLM Driven Embodied Agents With Contextual Backdoor Attacks.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2025

Hard-Label Black-Box Adversarial Attacks for Implicit Scene Interactions.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2025

FOADA: Toward Robust Open-World Mobile App Fingerprinting.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2025

Fairness Mediator: Neutralize Stereotype Associations to Mitigate Bias in Large Language Models.

[BibT_eX]

[DOI]

Proc. ACM Softw. Eng., 2025

Bridging the Task Gap: Multi-task Adversarial Transferability in CLIP and Its Derivatives.

[BibT_eX]

[DOI]

Proceedings of the Pattern Recognition and Computer Vision - 8th Chinese Conference, 2025

Manipulating Multimodal Agents via Cross-Modal Prompt Injection.

[BibT_eX]

[DOI]

Proceedings of the 33rd ACM International Conference on Multimedia, 2025

MetAdv: A Unified and Interactive Adversarial Testing Platform for Autonomous Driving.

[BibT_eX]

[DOI]

Proceedings of the 33rd ACM International Conference on Multimedia, 2025

Physical Adversarial Camouflage Through Gradient Calibration and Regularization.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence, 2025

BDefects4NN: A Backdoor Defect Database for Controlled Localization Studies in Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 47th IEEE/ACM International Conference on Software Engineering, 2025

ICLShield: Exploring and Mitigating In-Context Learning Backdoor Attacks.

[BibT_eX]

[DOI]

Proceedings of the Forty-second International Conference on Machine Learning, 2025

NoVo: Norm Voting off Hallucinations with Attention Heads in Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Towards a 3D Transfer-Based Black-Box Attack via Critical Feature Guidance.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

3D Gaussian Splatting Driven Multi-View Robust Physical Adversarial Camouflage Generation.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

Gradient-Reweighted Adversarial Camouflage for Physical Object Detection Evasion.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

CopyrightShield: Enhancing Diffusion Model Security Against Copyright Infringement Attacks.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF International Conference on Computer Vision, 2025

Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2025, 2025

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

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

Interpreting Object-level Foundation Models via Visual Precision Search.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2025

ELBA-Bench: An Efficient Learning Backdoor Attacks Benchmark for Large Language Models.

[BibT_eX]

[DOI]

Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

2024

Patch is enough: naturalistic adversarial patch against vision-language pre-training models.

[BibT_eX]

[DOI]

Vis. Intell., 2024

Red Pill and Blue Pill: Controllable Website Fingerprinting Defense via Dynamic Backdoor Learning.

[BibT_eX]

[DOI]

CoRR, 2024

CopyrightShield: Spatial Similarity Guided Backdoor Defense against Copyright Infringement in Diffusion Models.

[BibT_eX]

[DOI]

CoRR, 2024

Visual Adversarial Attack on Vision-Language Models for Autonomous Driving.

[BibT_eX]

[DOI]

CoRR, 2024

Interpreting Object-level Foundation Models via Visual Precision Search.

[BibT_eX]

[DOI]

CoRR, 2024

Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats.

[BibT_eX]

[DOI]

CoRR, 2024

CleanerCLIP: Fine-grained Counterfactual Semantic Augmentation for Backdoor Defense in Contrastive Learning.

[BibT_eX]

[DOI]

CoRR, 2024

Adversarial Backdoor Defense in CLIP.

[BibT_eX]

[DOI]

CoRR, 2024

Module-wise Adaptive Adversarial Training for End-to-end Autonomous Driving.

[BibT_eX]

[DOI]

CoRR, 2024

Compromising Embodied Agents with Contextual Backdoor Attacks.

[BibT_eX]

[DOI]

CoRR, 2024

Revisiting Backdoor Attacks against Large Vision-Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

LanEvil: Benchmarking the Robustness of Lane Detection to Environmental Illusions.

[BibT_eX]

[DOI]

CoRR, 2024

Environmental Matching Attack Against Unmanned Aerial Vehicles Object Detection.

[BibT_eX]

[DOI]

Dehong Kong

Siyuan Liang

Wenqi Ren

CoRR, 2024

Object Detectors in the Open Environment: Challenges, Solutions, and Outlook.

[BibT_eX]

[DOI]

CoRR, 2024

Unlearning Backdoor Threats: Enhancing Backdoor Defense in Multimodal Contrastive Learning via Local Token Unlearning.

[BibT_eX]

[DOI]

CoRR, 2024

Semantic Mirror Jailbreak: Genetic Algorithm Based Jailbreak Prompts Against Open-source LLMs.

[BibT_eX]

[DOI]

CoRR, 2024

VL-Trojan: Multimodal Instruction Backdoor Attacks against Autoregressive Visual Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack.

[BibT_eX]

[DOI]

Mingli Zhu

Siyuan Liang

Baoyuan Wu

Proceedings of the Advances in Neural Information Processing Systems 37: Annual Conference on Neural Information Processing Systems 2024, 2024

Towards Robust Physical-world Backdoor Attacks on Lane Detection.

[BibT_eX]

[DOI]

Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning.

[BibT_eX]

[DOI]

Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

<i>LanEvil</i>: Benchmarking the Robustness of Lane Detection to Environmental Illusions.

[BibT_eX]

[DOI]

Proceedings of the 32nd ACM International Conference on Multimedia, MM 2024, Melbourne, VIC, Australia, 28 October 2024, 2024

Towards Robust Object Detection: Identifying and Removing Backdoors via Module Inconsistency Analysis.

[BibT_eX]

[DOI]

Xianda Zhang

Siyuan Liang

Chengyang Li

Proceedings of the Pattern Recognition - 27th International Conference, 2024

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Less is More: Fewer Interpretable Region via Submodular Subset Selection.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Hide in Thicket: Generating Imperceptible and Rational Adversarial Perturbations on 3D Point Clouds.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

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

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

Does Few-Shot Learning Suffer from Backdoor Attacks?

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

Learning to Optimize Permutation Flow Shop Scheduling via Graph-Based Imitation Learning.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Privacy-Enhancing Face Obfuscation Guided by Semantic-Aware Attribution Maps.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2023

SA-Attack: Improving Adversarial Transferability of Vision-Language Pre-training Models via Self-Augmentation.

[BibT_eX]

[DOI]

CoRR, 2023

X-Adv: Physical Adversarial Object Attacks against X-ray Prohibited Item Detection.

[BibT_eX]

[DOI]

Proceedings of the 32nd USENIX Security Symposium, 2023

Exploring Inconsistent Knowledge Distillation for Object Detection with Data Augmentation.

[BibT_eX]

[DOI]

Proceedings of the 31st ACM International Conference on Multimedia, 2023

Isolation and Induction: Training Robust Deep Neural Networks against Model Stealing Attacks.

[BibT_eX]

[DOI]

Proceedings of the 31st ACM International Conference on Multimedia, 2023

Face Encryption via Frequency-Restricted Identity-Agnostic Attacks.

[BibT_eX]

[DOI]

Proceedings of the 31st ACM International Conference on Multimedia, 2023

Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

Improving Robust Fariness via Balance Adversarial Training.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

Generating Transferable 3D Adversarial Point Cloud via Random Perturbation Factorization.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023

2022

Learning to Optimize Permutation Flow Shop Scheduling via Graph-based Imitation Learning.

[BibT_eX]

[DOI]

CoRR, 2022

Exploring the Relationship between Architecture and Adversarially Robust Generalization.

[BibT_eX]

[DOI]

CoRR, 2022

Rethinking Data Augmentation in Knowledge Distillation for Object Detection.

[BibT_eX]

[DOI]

CoRR, 2022

Improving Robust Fairness via Balance Adversarial Training.

[BibT_eX]

[DOI]

CoRR, 2022

Adaptive Perturbation Generation for Multiple Backdoors Detection.

[BibT_eX]

[DOI]

CoRR, 2022

Imitated Detectors: Stealing Knowledge of Black-box Object Detectors.

[BibT_eX]

[DOI]

Proceedings of the MM '22: The 30th ACM International Conference on Multimedia, Lisboa, Portugal, October 10, 2022

A Large-Scale Multiple-objective Method for Black-box Attack Against Object Detection.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2022, 2022

2021

Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detection.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

2020

Efficient Adversarial Attacks for Visual Object Tracking.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

2019

Transferable Adversarial Attacks for Image and Video Object Detection.

[BibT_eX]

[DOI]

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, 2019

2018

Transferable Adversarial Attacks for Image and Video Object Detection.

[BibT_eX]

[DOI]

CoRR, 2018

Siyuan Liang

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...