English
Related papers

Related papers: Vulnerabilities in AI Code Generators: Exploring T…

200 papers

While finetuning AI agents on interaction data -- such as web browsing or tool use -- improves their capabilities, it also introduces critical security vulnerabilities within the agentic AI supply chain. We show that adversaries can…

LLMs produce harmful and undesirable behavior when trained on datasets containing even a small fraction of poisoned data. We demonstrate that GPT models remain vulnerable to fine-tuning on poisoned data, even when safeguarded by moderation…

Cryptography and Security · Computer Science 2025-07-18 Dillon Bowen , Brendan Murphy , Will Cai , David Khachaturov , Adam Gleave , Kellin Pelrine

Data poisoning attacks, in which a malicious adversary aims to influence a model by injecting "poisoned" data into the training process, have attracted significant recent attention. In this work, we take a closer look at existing poisoning…

Machine Learning · Computer Science 2024-02-16 Yiwei Lu , Gautam Kamath , Yaoliang Yu

Deep learning models have gained popularity for conducting various tasks involving source code. However, their black-box nature raises concerns about potential risks. One such risk is a poisoning attack, where an attacker intentionally…

Cryptography and Security · Computer Science 2025-03-18 Ehab Ghannoum , Mohammad Ghafari

With tools like GitHub Copilot, automatic code suggestion is no longer a dream in software engineering. These tools, based on large language models, are typically trained on massive corpora of code mined from unvetted public sources. As a…

Cryptography and Security · Computer Science 2024-01-25 Hojjat Aghakhani , Wei Dai , Andre Manoel , Xavier Fernandes , Anant Kharkar , Christopher Kruegel , Giovanni Vigna , David Evans , Ben Zorn , Robert Sim

Due to significant improvements in performance in recent years, neural networks are currently used for an ever-increasing number of applications. However, neural networks have the drawback that their decisions are not readily interpretable…

Cryptography and Security · Computer Science 2020-05-15 Christian Berghoff

We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak significant private details of training points belonging to other…

Cryptography and Security · Computer Science 2022-10-07 Florian Tramèr , Reza Shokri , Ayrton San Joaquin , Hoang Le , Matthew Jagielski , Sanghyun Hong , Nicholas Carlini

Deep Learning-based code generators have seen significant advancements in recent years. Tools such as GitHub Copilot are used by thousands of developers with the main promise of a boost in productivity. However, researchers have recently…

Software Engineering · Computer Science 2025-03-17 Cristina Improta , Rosalia Tufano , Pietro Liguori , Domenico Cotroneo , Gabriele Bavota

Preference learning is a central component for aligning current LLMs, but this process can be vulnerable to data poisoning attacks. To address this concern, we introduce PoisonBench, a benchmark for evaluating large language models'…

Cryptography and Security · Computer Science 2025-06-09 Tingchen Fu , Mrinank Sharma , Philip Torr , Shay B. Cohen , David Krueger , Fazl Barez

As machine learning models become increasingly complex, concerns about their robustness and trustworthiness have become more pressing. A critical vulnerability of these models is data poisoning attacks, where adversaries deliberately alter…

Machine Learning · Computer Science 2024-10-14 Isha Gupta , Hidde Lycklama , Emanuel Opel , Evan Rose , Anwar Hithnawi

Large language models (LLMs) have brought significant advancements to code generation and code repair, benefiting both novice and experienced developers. However, their training using unsanitized data from open-source repositories, like…

Software Engineering · Computer Science 2024-07-08 Jiexin Wang , Xitong Luo , Liuwen Cao , Hongkui He , Hailin Huang , Jiayuan Xie , Adam Jatowt , Yi Cai

Semi-supervised machine learning models learn from a (small) set of labeled training examples, and a (large) set of unlabeled training examples. State-of-the-art models can reach within a few percentage points of fully-supervised training,…

Machine Learning · Computer Science 2021-08-11 Nicholas Carlini

With the advancement of IoT technology, many electronic devices are interconnected through networks, communicating with each other and performing specific roles. However, as numerous devices join networks, the threat of cyberattacks also…

Cryptography and Security · Computer Science 2023-11-28 Sangbeom Park , Jaesung Lee , Jeong Do Yoo , Min Geun Song , Hyosun Lee , Jaewoong Choi , Chaeyeon Sagong , Huy Kang Kim

With the capability to write convincing and fluent natural language and generate code, Foundation Models present dual-use concerns broadly and within the cyber domain specifically. Generative AI has already begun to impact cyberspace…

Cryptography and Security · Computer Science 2024-10-25 Kade M. Heckel , Adrian Weller

Collecting training data from untrusted sources exposes machine learning services to poisoning adversaries, who maliciously manipulate training data to degrade the model accuracy. When trained on offline datasets, poisoning adversaries have…

Machine Learning · Computer Science 2021-10-27 Tianyu Pang , Xiao Yang , Yinpeng Dong , Hang Su , Jun Zhu

As machine learning (ML) classifiers increasingly oversee the automated monitoring of network traffic, studying their resilience against adversarial attacks becomes critical. This paper focuses on poisoning attacks, specifically backdoor…

Cryptography and Security · Computer Science 2023-06-05 Giorgio Severi , Simona Boboila , Alina Oprea , John Holodnak , Kendra Kratkiewicz , Jason Matterer

Federated learning (FL) is vulnerable to data poisoning attacks due to its distributed nature. Although recent GAN-based data poisoning methods have indicated the potential of using generative AI to generate seemingly legitimate poisoned…

Cryptography and Security · Computer Science 2026-05-18 Wei Sun , Yijun Chen , Bo Gao , Ke Xiong , Yuwei Wang , Pingyi Fan , Khaled Ben Letaief

AI-powered programming language generation (PLG) models have gained increasing attention due to their ability to generate source code of programs in a few seconds with a plain program description. Despite their remarkable performance, many…

Cryptography and Security · Computer Science 2023-05-23 Wanlun Ma , Yiliao Song , Minhui Xue , Sheng Wen , Yang Xiang

Data poisoning is a type of adversarial attack on training data where an attacker manipulates a fraction of data to degrade the performance of machine learning model. Therefore, applications that rely on external data-sources for training…

Machine Learning · Computer Science 2021-04-28 Sanjay Seetharaman , Shubham Malaviya , Rosni KV , Manish Shukla , Sachin Lodha

Neural code models (NCMs) have demonstrated extraordinary capabilities in code intelligence tasks. Meanwhile, the security of NCMs and NCMs-based systems has garnered increasing attention. In particular, NCMs are often trained on…

Software Engineering · Computer Science 2025-02-25 Weisong Sun , Yuchen Chen , Mengzhe Yuan , Chunrong Fang , Zhenpeng Chen , Chong Wang , Yang Liu , Baowen Xu , Zhenyu Chen
‹ Prev 1 3 4 5 6 7 10 Next ›