Siyuan Cheng

Orcid: 0009-0006-0903-6917

Affiliations:

Purdue University, Department of Computer Science, West Lafayette, IN, USA

According to our database¹, Siyuan Cheng authored at least 39 papers between 2020 and 2025.

Collaborative distances:

Dijkstra number² of four.
Erdős number³ of four.

Timeline

Legend:

Book

In proceedings

Article

PhD thesis

Dataset

Other

Bibliography

2025

CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs.

[BibT_eX]

[DOI]

CoRR, June, 2025

SOFT: Selective Data Obfuscation for Protecting LLM Fine-tuning against Membership Inference Attacks.

[BibT_eX]

[DOI]

CoRR, June, 2025

BAIT: Large Language Model Backdoor Scanning by Inverting Attack Target.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2025

A Systematic Threat Modeling of LLM Applications.

[BibT_eX]

[DOI]

Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering, 2025

Unleashing the Power of Generative Model in Recovering Variable Names from Stripped Binary.

[BibT_eX]

[DOI]

Proceedings of the 32nd Annual Network and Distributed System Security Symposium, 2025

CENSOR: Defense Against Gradient Inversion via Orthogonal Subspace Bayesian Sampling.

[BibT_eX]

[DOI]

Proceedings of the 32nd Annual Network and Distributed System Security Symposium, 2025

CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI.

[BibT_eX]

[DOI]

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

System Prompt Hijacking via Permutation Triggers in LLM Supply Chains.

[BibT_eX]

[DOI]

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

2024

ASPIRER: Bypassing System Prompts With Permutation-based Backdoors in LLMs.

[BibT_eX]

[DOI]

CoRR, 2024

DIGIMON: Diagnosis and Mitigation of Sampling Skew for Reinforcement Learning based Meta-Planner in Robot Navigation.

[BibT_eX]

[DOI]

CoRR, 2024

Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia.

[BibT_eX]

[DOI]

CoRR, 2024

Opening A Pandora's Box: Things You Should Know in the Era of Custom GPTs.

[BibT_eX]

[DOI]

CoRR, 2024

Rethinking the Invisible Protection against Unauthorized Image Usage in Stable Diffusion.

[BibT_eX]

[DOI]

Proceedings of the 33rd USENIX Security Symposium, 2024

On Large Language Models' Resilience to Coercive Interrogation.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2024

Exploring the Orthogonality and Linearity of Backdoor Attacks.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2024

OdScan: Backdoor Scanning for Object Detection Models.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2024

BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2024, 2024

ROCAS: Root Cause Analysis of Autonomous Driving Accidents via Cyber-Physical Co-mutation.

[BibT_eX]

[DOI]

Proceedings of the 39th IEEE/ACM International Conference on Automated Software Engineering, 2024

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

Lotus: Evasive and Resilient Backdoor Attacks through Sub-Partitioning.

[BibT_eX]

[DOI]

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

Exploring Inherent Backdoors in Deep Learning Models.

[BibT_eX]

[DOI]

Proceedings of the Annual Computer Security Applications Conference, 2024

Elijah: Eliminating Backdoors Injected in Diffusion Models via Distribution Shift.

[BibT_eX]

[DOI]

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

2023

Make Them Spill the Beans! Coercive Knowledge Extraction from (Production) LLMs.

[BibT_eX]

[DOI]

CoRR, 2023

LmPa: Improving Decompilation by Synergy of Large Language Model and Program Analysis.

[BibT_eX]

[DOI]

CoRR, 2023

Hard-label Black-box Universal Adversarial Patch Attack.

[BibT_eX]

[DOI]

Proceedings of the 32nd USENIX Security Symposium, 2023

ImU: Physical Impersonating Attack for Face Recognition System with Natural Style Changes.

[BibT_eX]

[DOI]

Proceedings of the 44th IEEE Symposium on Security and Privacy, 2023

PEM: Representing Binary Program Semantics for Similarity Analysis via a Probabilistic Execution Model.

[BibT_eX]

[DOI]

Proceedings of the 31st ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2023

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

BEAGLE: Forensics of Deep Learning Backdoor Attack for Better Defense.

[BibT_eX]

[DOI]

Proceedings of the 30th Annual Network and Distributed System Security Symposium, 2023

Improving Binary Code Similarity Transformer Models by Semantics-Driven Instruction Deemphasis.

[BibT_eX]

[DOI]

Proceedings of the 32nd ACM SIGSOFT International Symposium on Software Testing and Analysis, 2023

FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

MEDIC: Remove Model Backdoors via Importance Driven Cloning.

[BibT_eX]

[DOI]

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

Detecting Backdoors in Pre-trained Encoders.

[BibT_eX]

[DOI]

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

2022

Backdoor Vulnerabilities in Normally Trained Deep Learning Models.

[BibT_eX]

[DOI]

CoRR, 2022

DECK: Model Hardening for Defending Pervasive Backdoors.

[BibT_eX]

[DOI]

CoRR, 2022

2021

Backdoor Scanning for Deep Neural Networks through K-Arm Optimization.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Towards Feature Space Adversarial Attack by Style Perturbation.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

Deep Feature Space Trojan Attack of Neural Networks by Controlled Detoxification.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

Towards Feature Space Adversarial Attack.

[BibT_eX]

[DOI]

CoRR, 2020

Siyuan Cheng

Timeline

Legend:

Links

Online presence:

On csauthors.net:

Bibliography

Loading...