English
Related papers

Related papers: Signature in Code Backdoor Detection, how far are …

200 papers

Large language models (LLMs) have seen significant advancements, achieving superior performance in various Natural Language Processing (NLP) tasks. However, they remain vulnerable to backdoor attacks, where models behave normally for…

Computation and Language · Computer Science 2025-08-29 Chen Chen , Yuchen Sun , Jiaxin Gao , Xueluan Gong , Qian Wang , Ziyao Wang , Yongsen Zheng , Kwok-Yan Lam

Binary code analysis plays a pivotal role in various software security applications, such as software maintenance, malware detection, software vulnerability discovery, patch analysis, etc. However, unlike source code, understanding binary…

Software Engineering · Computer Science 2024-10-25 Xiuwei Shang , Shaoyin Cheng , Guoqiang Chen , Yanming Zhang , Li Hu , Xiao Yu , Gangyang Li , Weiming Zhang , Nenghai Yu

Recent advances confirm that large language models (LLMs) can achieve state-of-the-art performance across various tasks. However, due to the resource-intensive nature of training LLMs from scratch, it is urgent and crucial to protect the…

Cryptography and Security · Computer Science 2026-03-04 Zhiguang Yang , Hanzhou Wu

Backdoor attacks implant hidden behaviors into models by poisoning training data or modifying the model directly. These attacks aim to maintain high accuracy on benign inputs while causing misclassification when a specific trigger is…

Cryptography and Security · Computer Science 2025-12-10 Jianyao Yin , Luca Arnaboldi , Honglong Chen , Pascal Berrang , Mark Ryan

Backdoor attacks poison the training data, causing the model to behave normally on clean inputs but predict attacker-chosen labels when trigger patterns are embedded into the input samples. Defending against such attacks is highly…

Cryptography and Security · Computer Science 2026-04-28 Wei Guo , Maura Pintor , Ambra Demontis , Battista Biggio

Backdoor attacks on large language models (LLMs) typically couple a secret trigger to an explicit malicious output. We show that this explicit association is unnecessary for common LLMs. We introduce a compliance-only backdoor: supervised…

Machine Learning · Computer Science 2025-11-18 Yuting Tan , Yi Huang , Zhuo Li

As ML models become increasingly complex and integral to high-stakes domains such as finance and healthcare, they also become more susceptible to sophisticated adversarial attacks. We investigate the threat posed by undetectable backdoors,…

Machine Learning · Computer Science 2024-09-10 Alkis Kalavasis , Amin Karbasi , Argyris Oikonomou , Katerina Sotiraki , Grigoris Velegkas , Manolis Zampetakis

Large Language Models (LLMs) demonstrate impressive capabilities across various fields, yet their increasing use raises critical security concerns. This article reviews recent literature addressing key issues in LLM security, with a focus…

Cryptography and Security · Computer Science 2025-11-26 Benji Peng , Keyu Chen , Ming Li , Pohsun Feng , Ziqian Bi , Junyu Liu , Xinyuan Song , Qian Niu

Can we trust Large Language Models (LLMs) to accurately predict scam? This paper investigates the vulnerabilities of LLMs when facing adversarial scam messages for the task of scam detection. We addressed this issue by creating a…

Cryptography and Security · Computer Science 2025-11-05 Chen-Wei Chang , Shailik Sarkar , Shutonu Mitra , Qi Zhang , Hossein Salemi , Hemant Purohit , Fengxiu Zhang , Michin Hong , Jin-Hee Cho , Chang-Tien Lu

Code models, such as CodeBERT and CodeT5, offer general-purpose representations of code and play a vital role in supporting downstream automated software engineering tasks. Most recently, code models were revealed to be vulnerable to…

Cryptography and Security · Computer Science 2023-08-30 Zhou Yang , Bowen Xu , Jie M. Zhang , Hong Jin Kang , Jieke Shi , Junda He , David Lo

Software developers frequently hard-code credentials such as passwords, generic secrets, private keys, and generic tokens in software repositories, even though it is strictly advised against due to the severe threat to the security of the…

Cryptography and Security · Computer Science 2025-06-17 Chidera Biringa , Gokhan Kul

The growing dependence on machine learning in real-world applications emphasizes the importance of understanding and ensuring its safety. Backdoor attacks pose a significant security risk due to their stealthy nature and potentially serious…

Cryptography and Security · Computer Science 2023-10-19 Ganghua Wang , Xun Xian , Jayanth Srinivasa , Ashish Kundu , Xuan Bi , Mingyi Hong , Jie Ding

Interest in poisoning attacks and backdoors recently resurfaced for Deep Learning (DL) applications. Several successful defense mechanisms have been recently proposed for Convolutional Neural Networks (CNNs), for example in the context of…

Cryptography and Security · Computer Science 2020-04-07 Maximilian Bachl , Alexander Hartl , Joachim Fabini , Tanja Zseby

Backdoor attacks pose a serious threat to deep reinforcement learning (DRL). Current defenses typically rely on reward anomalies to reverse-engineer triggers and model finetuning to remove backdoors. However, complex trigger patterns…

Artificial Intelligence · Computer Science 2026-05-08 Yinbo Yu , Xueyu Yin , Jiadai Wang , Chunwei Tian , Sai Xu , Qi Zhu , Daoqiang Zhang

Large language models (LLMs) have achieved remarkable success across a wide range of natural language processing tasks, demonstrating human-level performance in text generation, reasoning, and question answering. However, training such…

Cryptography and Security · Computer Science 2025-11-17 Yanbo Dai , Zongjie Li , Zhenlan Ji , Shuai Wang

Backdoor attacks are emerging threats to deep neural networks, which typically embed malicious behaviors into a victim model by injecting poisoned samples. Adversaries can activate the injected backdoor during inference by presenting the…

Cryptography and Security · Computer Science 2025-12-05 Bingyin Zhao , Yingjie Lao

Large Language Models (LLMs), while powerful, are built and trained to process a single text input. In common applications, multiple inputs can be processed by concatenating them together into a single stream of text. However, the LLM is…

Cryptography and Security · Computer Science 2024-03-25 Keegan Hines , Gary Lopez , Matthew Hall , Federico Zarfati , Yonatan Zunger , Emre Kiciman

Large Language Models (LLMs) remain vulnerable to prompt injection attacks, representing the most significant security threat in production deployments. We present Prompt Fencing, a novel architectural approach that applies cryptographic…

Cryptography and Security · Computer Science 2025-11-26 Steven Peh

Software obfuscation and encryption present persistent challenges for program comprehension and security analysis, particularly when adversaries conceal Indicators of Compromise (IoCs) such as IP addresses within source code. While Large…

Cryptography and Security · Computer Science 2026-05-11 Jaime Morales , Sergio Pastrana , Juan Tapiador

A rapidly growing number of applications rely on a small set of closed-source language models (LMs). This dependency might introduce novel security risks if LMs develop self-recognition capabilities. Inspired by human identity verification…

Computation and Language · Computer Science 2024-10-11 Tim R. Davidson , Viacheslav Surkov , Veniamin Veselovsky , Giuseppe Russo , Robert West , Caglar Gulcehre