Shiqing Ma

IEEE Trans. Big Data, June, 2026

REBENCH: A Procedural, Fair-by-Construction Benchmark for LLMs on Stripped-Binary Types and Names (Extended Version).

[BibT_eX]

[DOI]

CoRR, April, 2026

Train in Vain: Functionality-Preserving Poisoning to Prevent Unauthorized Use of Code Datasets.

[BibT_eX]

[DOI]

CoRR, April, 2026

Weaponizing the Commons: A Taxonomy and Detection Framework of Abuse on GitHub.

[BibT_eX]

[DOI]

CoRR, April, 2026

Domain-Specialized Tree of Thought through Plug-and-Play Predictors.

[BibT_eX]

[DOI]

CoRR, March, 2026

Trojans in Artificial Intelligence (TrojAI) Final Report.

[BibT_eX]

[DOI]

CoRR, February, 2026

JailGuard: A Universal Detection Framework for Prompt-based Attacks on LLM Systems.

[BibT_eX]

[DOI]

ACM Trans. Softw. Eng. Methodol., January, 2026

Small Symbols, Big Risks: Exploring Emoticon Semantic Confusion in Large Language Models.

[BibT_eX]

[DOI]

CoRR, January, 2026

From Chaos to Clarity: A Knowledge Graph-Driven Audit Dataset Generation Framework for LLM Unlearning.

[BibT_eX]

[DOI]

Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025

PROMPTMINER: Black-Box Prompt Stealing against Text-to-Image Generative Models via Reinforcement Learning and Fuzz Optimization.

[BibT_eX]

[DOI]

Bruno Castro da Silva

Juan Zhai

CoRR, November, 2025

Rethinking Provenance Completeness with a Learning-Based Linux Scheduler.

[BibT_eX]

[DOI]

Jinsong Mao

Benjamin E. Ujcich

Mohammadreza Teymoorianfard

CoRR, October, 2025

Rethinking Technology Stack Selection with AI Coding Proficiency.

[BibT_eX]

[DOI]

CoRR, September, 2025

Mitigating Stylistic Biases of Machine Translation Systems via Monolingual Corpora Only.

[BibT_eX]

[DOI]

CoRR, July, 2025

Disappearing Ink: Obfuscation Breaks N-gram Code Watermarks in Theory and Practice.

[BibT_eX]

[DOI]

CoRR, July, 2025

ASSURE: Metamorphic Testing for AI-powered Browser Extensions.

[BibT_eX]

[DOI]

CoRR, July, 2025

The Foundation Cracks: A Comprehensive Study on Bugs and Testing Practices in LLM Libraries.

[BibT_eX]

[DOI]

CoRR, June, 2025

EDITOR: Effective and Interpretable Prompt Inversion for Text-to-Image Diffusion Models.

[BibT_eX]

[DOI]

CoRR, June, 2025

DREAM: Debugging and Repairing AutoML Pipelines.

[BibT_eX]

[DOI]

ACM Trans. Softw. Eng. Methodol., May, 2025

VIDSTAMP: A Temporally-Aware Watermark for Ownership and Integrity in Video Diffusion Models.

[BibT_eX]

[DOI]

CoRR, May, 2025

Exposing Product Bias in LLM Investment Recommendation.

[BibT_eX]

[DOI]

CoRR, March, 2025

Holistic Audit Dataset Generation for LLM Unlearning via Knowledge Graph Traversal and Redundancy Removal.

[BibT_eX]

[DOI]

CoRR, February, 2025

Safety at Scale: A Comprehensive Survey of Large Model Safety.

[BibT_eX]

[DOI]

CoRR, February, 2025

Unveiling Provider Bias in Large Language Models for Code Generation.

[BibT_eX]

[DOI]

CoRR, January, 2025

An Automated Monitoring and Repairing System for DNN Training.

[BibT_eX]

[DOI]

IEEE Trans. Dependable Secur. Comput., 2025

DeCoMa: Detecting and Purifying Code Dataset Watermarks through Dual Channel Code Abstraction.

[BibT_eX]

[DOI]

Proc. ACM Softw. Eng., 2025

Safety at Scale: A Comprehensive Survey of Large Model and Agent Safety.

[BibT_eX]

[DOI]

Found. Trends Priv. Secur., 2025

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

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2025

Repurposing Neural Networks for Efficient Cryptographic Computation.

[BibT_eX]

[DOI]

Xin Jin

Zhiqiang Lin

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

Data-centric NLP Backdoor Defense from the Lens of Memorization.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, New Mexico, USA, April 29, 2025

An Optimizable Suffix Is Worth A Thousand Templates: Efficient Black-box Jailbreaking without Affirmative Phrases via LLM as Optimizer.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2025, Albuquerque, New Mexico, USA, April 29, 2025

STAFF: Speculative Coreset Selection for Task-Specific Fine-tuning.

[BibT_eX]

[DOI]

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

Invisible Backdoor Attack against Self-supervised Learning.

[BibT_eX]

[DOI]

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

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

[BibT_eX]

[DOI]

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

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

[BibT_eX]

[DOI]

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

Uncertainty Quantification for Multiple-Choice Questions is Just One-Token Deep.

[BibT_eX]

[DOI]

Proceedings of the 34th ACM International Conference on Information and Knowledge Management, 2025

The Invisible Hand: Unveiling Provider Bias in Large Language Models for Code Generation.

[BibT_eX]

[DOI]

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

Token-Budget-Aware LLM Reasoning.

[BibT_eX]

[DOI]

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

2024

COSTELLO: Contrastive Testing for Embedding-Based Large Language Model as a Service Embeddings.

[BibT_eX]

[DOI]

Proc. ACM Softw. Eng., 2024

Continuous Concepts Removal in Text-to-image Diffusion Models.

[BibT_eX]

[DOI]

CoRR, 2024

Bias Similarity Across Large Language Models.

[BibT_eX]

[DOI]

Hyejun Jeong

Mohammadreza Teymoorianfard

CoRR, 2024

Speculative Coreset Selection for Task-Specific Fine-tuning.

[BibT_eX]

[DOI]

CoRR, 2024

Unlocking Adversarial Suffix Optimization Without Affirmative Phrases: Efficient Black-box Jailbreaking via LLM as Optimizer.

[BibT_eX]

[DOI]

CoRR, 2024

Uncertainty is Fragile: Manipulating Uncertainty in Large Language Models.

[BibT_eX]

[DOI]

CoRR, 2024

CITADEL: Context Similarity Based Deep Learning Framework Bug Finding.

[BibT_eX]

[DOI]

CoRR, 2024

MeanSparse: Post-Training Robustness Enhancement Through Mean-Centered Feature Sparsification.

[BibT_eX]

[DOI]

Sajjad Amini

CoRR, 2024

From Effectiveness to Efficiency: Comparative Evaluation of Code Generated by LCGMs for Bilingual Programming Questions.

[BibT_eX]

[DOI]

CoRR, 2024

Towards Imperceptible Backdoor Attack in Self-supervised Learning.

[BibT_eX]

[DOI]

CoRR, 2024

SoK: Challenges and Opportunities in Federated Unlearning.

[BibT_eX]

[DOI]

Hyejun Jeong

CoRR, 2024

Rapid Optimization for Jailbreaking LLMs via Subconscious Exploitation and Echopraxia.

[BibT_eX]

[DOI]

CoRR, 2024

DREAM: Debugging and Repairing AutoML Pipelines.

[BibT_eX]

[DOI]

CoRR, 2024

Exploring the Orthogonality and Linearity of Backdoor Attacks.

[BibT_eX]

[DOI]

Proceedings of the IEEE Symposium on Security and Privacy, 2024

Distribution Preserving Backdoor Attack in Self-supervised Learning.

[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

Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering.

[BibT_eX]

[DOI]

Proceedings of the 31st Annual Network and Distributed System Security Symposium, 2024

Efficient DNN-Powered Software with Fair Sparse Models.

[BibT_eX]

[DOI]

Proceedings of the 33rd ACM SIGSOFT International Symposium on Software Testing and Analysis, 2024

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

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2024, 2024

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

[BibT_eX]

[DOI]

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

Merlin: Multi-tier Optimization of eBPF Code for Performance and Compactness.

[BibT_eX]

[DOI]

Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, 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

Finding Deviated Behaviors of the Compressed DNN Models for Image Classifications.

[BibT_eX]

[DOI]

ACM Trans. Softw. Eng. Methodol., September, 2023

autoMPI: Automated Multiple Perspective Attack Investigation With Semantics Aware Execution Partitioning.

[BibT_eX]

[DOI]

Mohannad Alhanahnah

Ashish Gehani

Vinod Yegneswaran

Somesh Jha

Xiangyu Zhang

IEEE Trans. Software Eng., April, 2023

How to Detect Unauthorized Data Usages in Text-to-image Diffusion Models.

[BibT_eX]

[DOI]

CoRR, 2023

Alteration-free and Model-agnostic Origin Attribution of Generated Images.

[BibT_eX]

[DOI]

CoRR, 2023

Gradient Shaping: Enhancing Backdoor Attack Against Reverse Engineering.

[BibT_eX]

[DOI]

CoRR, 2023

KENKU: Towards Efficient and Stealthy Black-box Adversarial Attacks against ASR Systems.

[BibT_eX]

[DOI]

Proceedings of the 32nd USENIX Security Symposium, 2023

AIRTAG: Towards Automated Attack Investigation by Unsupervised Learning with Log Texts.

[BibT_eX]

[DOI]

Proceedings of the 32nd USENIX Security Symposium, 2023

The Case for Learned Provenance Graph Storage Systems.

[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

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

[BibT_eX]

[DOI]

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

CILIATE: Towards Fairer Class-Based Incremental Learning by Dataset and Training Refinement.

[BibT_eX]

[DOI]

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

UNICORN: A Unified Backdoor Trigger Inversion Framework.

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 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

Get Your Cyber-Physical Tests Done! Data-Driven Vulnerability Assessment of Robotic Aerial Vehicles.

[BibT_eX]

[DOI]

Proceedings of the 53rd Annual IEEE/IFIP International Conference on Dependable Systems and Network, 2023

Detecting Backdoors in Pre-trained Encoders.

[BibT_eX]

[DOI]

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

NOTABLE: Transferable Backdoor Attacks Against Prompt-based NLP Models.

[BibT_eX]

[DOI]

Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2023

2022

Deep Learning Backdoors.

[BibT_eX]

[DOI]

Security and Artificial Intelligence, 2022

TnT Attacks! Universal Naturalistic Adversarial Patches Against Deep Neural Network Systems.

[BibT_eX]

[DOI]

IEEE Trans. Inf. Forensics Secur., 2022

Backdoor Vulnerabilities in Normally Trained Deep Learning Models.

[BibT_eX]

[DOI]

CoRR, 2022

Apple of Sodom: Hidden Backdoors in Superior Sentence Embeddings via Contrastive Learning.

[BibT_eX]

[DOI]

CoRR, 2022

Neural Network Trojans Analysis and Mitigation from the Input Domain.

[BibT_eX]

[DOI]

CoRR, 2022

Constrained Optimization with Dynamic Bound-scaling for Effective NLPBackdoor Defense.

[BibT_eX]

[DOI]

CoRR, 2022

Piccolo: Exposing Complex Backdoors in NLP Transformer Models.

[BibT_eX]

[DOI]

Proceedings of the 43rd IEEE Symposium on Security and Privacy, 2022

Rethinking the Reverse-engineering of Trojan Triggers.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

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

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, 2022

Achieving Both Model Accuracy and Robustness by Adversarial Training with Batch Norm Shaping.

[BibT_eX]

[DOI]

Brian Zhang

Proceedings of the 34th IEEE International Conference on Tools with Artificial Intelligence, 2022

Fairneuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons.

[BibT_eX]

[DOI]

Proceedings of the 44th IEEE/ACM 44th International Conference on Software Engineering, 2022

Constrained Optimization with Dynamic Bound-scaling for Effective NLP Backdoor Defense.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Dynamic Backdoor Attacks Against Machine Learning Models.

[BibT_eX]

[DOI]

Proceedings of the 7th IEEE European Symposium on Security and Privacy, 2022

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

[BibT_eX]

[DOI]

Zhenting Wang

Juan Zhai

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Better Trigger Inversion Optimization in Backdoor Scanning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

Complex Backdoor Detection by Symmetric Feature Differencing.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2021

To what extent do DNN-based image classification models make unreliable inferences?

[BibT_eX]

[DOI]

Empir. Softw. Eng., 2021

Fast Test Input Generation for Finding Deviated Behaviors in Compressed Deep Neural Network.

[BibT_eX]

[DOI]

CoRR, 2021

EX-RAY: Distinguishing Injected Backdoor from Natural Features in Neural Networks by Examining Differential Feature Symmetry.

[BibT_eX]

[DOI]

CoRR, 2021

ELISE: A Storage Efficient Logging System Powered by Redundancy Reduction and Representation Learning.

[BibT_eX]

[DOI]

Proceedings of the 30th USENIX Security Symposium, 2021

ATLAS: A Sequence-based Learning Approach for Attack Investigation.

[BibT_eX]

[DOI]

Proceedings of the 30th USENIX Security Symposium, 2021

SemFlow: Accurate Semantic Identification from Low-Level System Data.

[BibT_eX]

[DOI]

Proceedings of the Security and Privacy in Communication Networks, 2021

ALchemist: Fusing Application and Audit Logs for Precise Attack Provenance without Instrumentation.

[BibT_eX]

[DOI]

Vinod Yegneswaran

Ashish Gehani

Proceedings of the 28th Annual Network and Distributed System Security Symposium, 2021

AUTOTRAINER: An Automatic DNN Training Problem Detection and Repair System.

[BibT_eX]

[DOI]

Proceedings of the 43rd IEEE/ACM International Conference on Software Engineering, 2021

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

[BibT_eX]

[DOI]

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

BadNL: Backdoor Attacks against NLP Models with Semantic-preserving Improvements.

[BibT_eX]

[DOI]

Proceedings of the ACSAC '21: Annual Computer Security Applications Conference, Virtual Event, USA, December 6, 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

Deep Learning Backdoors.

[BibT_eX]

[DOI]

CoRR, 2020

BadNL: Backdoor Attacks Against NLP Models.

[BibT_eX]

[DOI]

CoRR, 2020

C2S: translating natural language comments to formal program specifications.

[BibT_eX]

[DOI]

Proceedings of the ESEC/FSE '20: 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020

Correlations between deep neural network model coverage criteria and model quality.

[BibT_eX]

[DOI]

Proceedings of the ESEC/FSE '20: 28th ACM Joint European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2020

UIScope: Accurate, Instrumentation-free, and Visible Attack Investigation for GUI Applications.

[BibT_eX]

[DOI]

Proceedings of the 27th Annual Network and Distributed System Security Symposium, 2020

FineLock: automatically refactoring coarse-grained locks into fine-grained locks.

[BibT_eX]

[DOI]

Proceedings of the ISSTA '20: 29th ACM SIGSOFT International Symposium on Software Testing and Analysis, 2020

CPC: automatically classifying and propagating natural language comments via program analysis.

[BibT_eX]

[DOI]

Proceedings of the ICSE '20: 42nd International Conference on Software Engineering, Seoul, South Korea, 27 June, 2020

TRADER: trace divergence analysis and embedding regulation for debugging recurrent neural networks.

[BibT_eX]

[DOI]

Proceedings of the ICSE '20: 42nd International Conference on Software Engineering, Seoul, South Korea, 27 June, 2020

2019

Testing Deep Learning Models for Image Analysis Using Object-Relevant Metamorphic Relations.

[BibT_eX]

[DOI]

CoRR, 2019

ProFuzzer: On-the-fly Input Type Probing for Better Zero-Day Vulnerability Discovery.

[BibT_eX]

[DOI]

Proceedings of the 2019 IEEE Symposium on Security and Privacy, 2019

Programming support for autonomizing software.

[BibT_eX]

[DOI]

Proceedings of the 40th ACM SIGPLAN Conference on Programming Language Design and Implementation, 2019

NIC: Detecting Adversarial Samples with Neural Network Invariant Checking.

[BibT_eX]

[DOI]

Proceedings of the 26th Annual Network and Distributed System Security Symposium, 2019

SLF: fuzzing without valid seed inputs.

[BibT_eX]

[DOI]

Proceedings of the 41st International Conference on Software Engineering, 2019

White-Box Program Tuning.

[BibT_eX]

[DOI]

Proceedings of the IEEE/ACM International Symposium on Code Generation and Optimization, 2019

ABS: Scanning Neural Networks for Back-doors by Artificial Brain Stimulation.

[BibT_eX]

[DOI]

Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, 2019

2018

Kernel-Supported Cost-Effective Audit Logging for Causality Tracking.

[BibT_eX]

[DOI]

Proceedings of the 2018 USENIX Annual Technical Conference, 2018

MODE: automated neural network model debugging via state differential analysis and input selection.

[BibT_eX]

[DOI]

Proceedings of the 2018 ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2018

Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samples.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 31: Annual Conference on Neural Information Processing Systems 2018, 2018

Trojaning Attack on Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 25th Annual Network and Distributed System Security Symposium, 2018

MCI : Modeling-based Causality Inference in Audit Logging for Attack Investigation.

[BibT_eX]

[DOI]

Ashish Gehani

Vinod Yegneswaran

Proceedings of the 25th Annual Network and Distributed System Security Symposium, 2018

Dual-force: understanding WebView malware via cross-language forced execution.

[BibT_eX]

[DOI]

Proceedings of the 33rd ACM/IEEE International Conference on Automated Software Engineering, 2018

Debugging with intelligence via probabilistic inference.

[BibT_eX]

[DOI]

Proceedings of the 40th International Conference on Software Engineering, 2018

Lprov: Practical Library-aware Provenance Tracing.

[BibT_eX]

[DOI]

Proceedings of the 34th Annual Computer Security Applications Conference, 2018

2017

MPI: Multiple Perspective Attack Investigation with Semantic Aware Execution Partitioning.

[BibT_eX]

[DOI]

Proceedings of the 26th USENIX Security Symposium, 2017

LAMP: data provenance for graph based machine learning algorithms through derivative computation.

[BibT_eX]

[DOI]

Proceedings of the 2017 11th Joint Meeting on Foundations of Software Engineering, 2017

A Hypervisor Level Provenance System to Reconstruct Attack Story Caused by Kernel Malware.

[BibT_eX]

[DOI]

Proceedings of the Security and Privacy in Communication Networks, 2017

2016

ProTracer: Towards Practical Provenance Tracing by Alternating Between Logging and Tainting.

[BibT_eX]

[DOI]