English
Related papers

Related papers: Backdoors in Code Summarizers: How Bad Is It?

200 papers

Backdoor attacks pose significant security risks for Large Language Models (LLMs), yet the internal mechanisms by which triggers operate remain poorly understood. We present the first mechanistic analysis of language-switching backdoors,…

Computation and Language · Computer Science 2026-02-16 Théo Lasnier , Wissam Antoun , Francis Kulumba , Djamé Seddah

Large Language Models (LLMs) have shown significant promise in real-world decision-making tasks for embodied artificial intelligence, especially when fine-tuned to leverage their inherent common sense and reasoning abilities while being…

Cryptography and Security · Computer Science 2025-05-01 Ruochen Jiao , Shaoyuan Xie , Justin Yue , Takami Sato , Lixu Wang , Yixuan Wang , Qi Alfred Chen , Qi Zhu

Large language model (LLM) unlearning has become a critical mechanism for removing undesired data, knowledge, or behaviors from pre-trained models while retaining their general utility. Yet, with the rise of open-weight LLMs, we ask: can…

Machine Learning · Computer Science 2025-10-21 Bingqi Shang , Yiwei Chen , Yihua Zhang , Bingquan Shen , Sijia Liu

Deep learning is becoming increasingly popular in real-life applications, especially in natural language processing (NLP). Users often choose training outsourcing or adopt third-party data and models due to data and computation resources…

Computation and Language · Computer Science 2022-11-23 Xuan Sheng , Zhaoyang Han , Piji Li , Xiangmao Chang

Deep neural networks are vulnerable to adversarial attacks, such as backdoor attacks in which a malicious adversary compromises a model during training such that specific behaviour can be triggered at test time by attaching a specific word…

Cryptography and Security · Computer Science 2022-10-21 You Guo , Jun Wang , Trevor Cohn

Agent ecosystems increasingly rely on installable skills to extend functionality, and some skills bundle learned model artifacts as part of their execution logic. This creates a supply-chain risk that is not captured by prompt injection or…

Cryptography and Security · Computer Science 2026-04-13 Guiyao Tie , Jiawen Shi , Pan Zhou , Lichao Sun

Backdoor attacks have become an emerging threat to NLP systems. By providing poisoned training data, the adversary can embed a "backdoor" into the victim model, which allows input instances satisfying certain textual patterns (e.g.,…

Computation and Language · Computer Science 2023-05-30 Jun Yan , Vansh Gupta , Xiang Ren

In this work, we investigate the concept of biometric backdoors: a template poisoning attack on biometric systems that allows adversaries to stealthily and effortlessly impersonate users in the long-term by exploiting the template update…

Cryptography and Security · Computer Science 2020-11-06 Giulio Lovisotto , Simon Eberz , Ivan Martinovic

Architectural backdoors pose an under-examined but critical threat to deep neural networks, embedding malicious logic directly into a model's computational graph. Unlike traditional data poisoning or parameter manipulation, architectural…

Cryptography and Security · Computer Science 2025-07-18 Victoria Childress , Josh Collyer , Jodie Knapp

Backdoor attacks threaten the deep learning supply chain by poisoning a small fraction of the training data so that a model behaves normally on clean inputs but misclassifies trigger-carrying inputs to an attacker-chosen target class.…

Cryptography and Security · Computer Science 2026-05-05 Yi Yang , Jinyang Huang , Binbin Liu , Feng-Qi Cui , Xiaokang Zhou , Zhi Liu , Jie Zhang , Meng Li

Backdoor attacks embed hidden malicious behaviors into deep learning models, which only activate and cause misclassifications on model inputs containing a specific trigger. Existing works on backdoor attacks and defenses, however, mostly…

Computer Vision and Pattern Recognition · Computer Science 2021-09-08 Emily Wenger , Josephine Passananti , Arjun Bhagoji , Yuanshun Yao , Haitao Zheng , Ben Y. Zhao

Backdoor attacks aim to surreptitiously insert malicious triggers into DNN models, granting unauthorized control during testing scenarios. Existing methods lack robustness against defense strategies and predominantly focus on enhancing…

Cryptography and Security · Computer Science 2024-12-03 Pengfei He , Yue Xing , Han Xu , Jie Ren , Yingqian Cui , Shenglai Zeng , Jiliang Tang , Makoto Yamada , Mohammad Sabokrou

Deep learning achieves outstanding results in many machine learning tasks. Nevertheless, it is vulnerable to backdoor attacks that modify the training set to embed a secret functionality in the trained model. The modified training samples…

Computer Vision and Pattern Recognition · Computer Science 2023-04-24 Gorka Abad , Jing Xu , Stefanos Koffas , Behrad Tajalli , Stjepan Picek , Mauro Conti

Backdoor attacks are a significant threat to the performance and integrity of pre-trained language models. Although such models are routinely fine-tuned for downstream NLP tasks, recent work shows they remain vulnerable to backdoor attacks…

Machine Learning · Computer Science 2025-08-28 Santosh Chapagain , Shah Muhammad Hamdi , Soukaina Filali Boubrahimi

Poisoning of data sets is a potential security threat to large language models that can lead to backdoored models. A description of the internal mechanisms of backdoored language models and how they process trigger inputs, e.g., when…

Machine Learning · Computer Science 2024-05-07 Max Lamparth , Anka Reuel

Although backdoor learning is an active research topic in the NLP domain, the literature lacks studies that systematically categorize and summarize backdoor attacks and defenses. To bridge the gap, we present a comprehensive and unifying…

Cryptography and Security · Computer Science 2023-02-15 Marwan Omar

Large Language Models (LLMs) have become integral to many applications, with system prompts serving as a key mechanism to regulate model behavior and ensure ethical outputs. In this paper, we introduce a novel backdoor attack that…

Cryptography and Security · Computer Science 2024-10-08 Lu Yan , Siyuan Cheng , Xuan Chen , Kaiyuan Zhang , Guangyu Shen , Zhuo Zhang , Xiangyu Zhang

We witness an increasing usage of AI-assistants even for routine (classroom) programming tasks. However, the code generated on basis of a so called "prompt" by the programmer does not always meet accepted security standards. On the one…

Software Engineering · Computer Science 2024-08-15 Stefan Goetz , Andreas Schaad

We conduct a systematic study of backdoor vulnerabilities in normally trained Deep Learning models. They are as dangerous as backdoors injected by data poisoning because both can be equally exploited. We leverage 20 different types of…

Cryptography and Security · Computer Science 2022-11-30 Guanhong Tao , Zhenting Wang , Siyuan Cheng , Shiqing Ma , Shengwei An , Yingqi Liu , Guangyu Shen , Zhuo Zhang , Yunshu Mao , Xiangyu Zhang

Backdoor attacks pose an important security threat to textual large language models. Exploring textual backdoor attacks not only helps reveal the potential security risks of models, but also promotes innovation and development of defense…

Cryptography and Security · Computer Science 2025-07-21 Yang Hou , Qiuling Yue , Lujia Chai , Guozhao Liao , Wenbao Han , Wei Ou