English
Related papers

Related papers: On Trojan Signatures in Large Language Models of C…

200 papers

Large language models (LLMs) excel in many tasks of software engineering, yet progress in leveraging them for vulnerability discovery has stalled in recent years. To understand this phenomenon, we investigate LLMs through the lens of…

Cryptography and Security · Computer Science 2025-09-24 Felix Weissberg , Lukas Pirch , Erik Imgrund , Jonas Möller , Thorsten Eisenhofer , Konrad Rieck

Model editing methods modify specific behaviors of Large Language Models by altering a small, targeted set of network weights and require very little data and compute. These methods can be used for malicious applications such as inserting…

Machine Learning · Computer Science 2025-09-08 Keltin Grimes , Marco Christiani , David Shriver , Marissa Connor

We present a Trojan (backdoor or trapdoor) attack that targets deep learning applications in wireless communications. A deep learning classifier is considered to classify wireless signals using raw (I/Q) samples as features and modulation…

Networking and Internet Architecture · Computer Science 2019-10-25 Kemal Davaslioglu , Yalin E. Sagduyu

Large Language Models (LLMs) have emerged as a popular choice in vulnerability detection studies given their foundational capabilities, open source availability, and variety of models, but have limited scalability due to extensive compute…

Software Engineering · Computer Science 2026-04-01 Miles Farmer , Ekincan Ufuktepe , Anne Watson , Hialo Muniz Carvalho , Vadim Okun , Zineb Maasaoui , Kannappan Palaniappan

The emergence of distributed manufacturing ecosystems for electronic hardware involving untrusted parties has given rise to diverse trust issues. In particular, IP piracy, overproduction, and hardware Trojan attacks pose significant threats…

Cryptography and Security · Computer Science 2020-10-13 Abhishek Nair , Patanjali SLPSK , Chester Rebeiro , Swarup Bhunia

The Syndrome Decoding problem is at the core of many code-based cryptosystems. In this paper, we study ternary Syndrome Decoding in large weight. This problem has been introduced in the Wave signature scheme but has never been thoroughly…

Cryptography and Security · Computer Science 2019-06-17 Rémi Bricout , André Chailloux , Thomas Debris-Alazard , Matthieu Lequesne

Code generation large language models (LLMs) are increasingly integrated into modern software development workflows. Recent work has shown that these models are vulnerable to backdoor and poisoning attacks that induce the generation of…

Cryptography and Security · Computer Science 2026-03-19 Shenao Yan , Shimaa Ahmed , Shan Jin , Sunpreet S. Arora , Yiwei Cai , Yizhen Wang , Yuan Hong

In this paper, we present a challenging code reasoning task: vulnerability detection. Large Language Models (LLMs) have shown promising results in natural-language and math reasoning, but state-of-the-art (SOTA) models reported only 54.5%…

Software Engineering · Computer Science 2025-01-09 Benjamin Steenhoek , Md Mahbubur Rahman , Monoshi Kumar Roy , Mirza Sanjida Alam , Hengbo Tong , Swarna Das , Earl T. Barr , Wei Le

Deep neural networks (DNNs) are vulnerable to "backdoor" poisoning attacks, in which an adversary implants a secret trigger into an otherwise normally functioning model. Detection of backdoors in trained models without access to the…

Machine Learning · Computer Science 2021-03-19 Todd Huster , Emmanuel Ekwedike

Large Language Models (LLMs) are widely deployed in real-world applications, yet little is known about their training dynamics at the token level. Evaluation typically relies on aggregated training loss, measured at the batch level, which…

Computation and Language · Computer Science 2024-10-17 Andrea Pinto , Tomer Galanti , Randall Balestriero

This study examines the impact of tokenized Java code length on the accuracy and explicitness of ten major LLMs in vulnerability detection. Using chi-square tests and known ground truth, we found inconsistencies across models: some, like…

Cryptography and Security · Computer Science 2025-02-04 Jie Lin , David Mohaisen

Vulnerability detection for C/C++ code increasingly relies on heavy representations such as code graphs and deep models, while many practical workflows still benefit from fast and reproducible ranking baselines for human triage. This…

Cryptography and Security · Computer Science 2026-05-07 Chun Yin Chiu

Existing Hardware Trojans (HT) detection methods face several critical limitations: logic testing struggles with scalability and coverage for large designs, side-channel analysis requires golden reference chips, and formal verification…

Cryptography and Security · Computer Science 2024-12-11 Md Omar Faruque , Peter Jamieson , Ahmad Patooghy , Abdel-Hameed A. Badawy

Malware detection increasingly relies on AI systems that integrate signature-based detection with machine learning. However, these components are typically developed and combined in isolation, missing opportunities to reduce data complexity…

Cryptography and Security · Computer Science 2025-08-14 Andrea Ponte , Luca Demetrio , Luca Oneto , Ivan Tesfai Ogbu , Battista Biggio , Fabio Roli

Code understanding models increasingly rely on pretrained language models (PLMs) and graph neural networks (GNNs), which capture complementary semantic and structural information. We conduct a controlled empirical study of PLM-GNN hybrids…

Software Engineering · Computer Science 2026-04-29 Mohamed Taoufik Kaouthar El Idrissi , Edward Zulkoski , Mohammad Hamdaqa

Modern tokenizers employ deterministic algorithms to map text into a single "canonical" token sequence, yet the same string can be encoded as many non-canonical tokenizations using the tokenizer vocabulary. In this work, we investigate the…

Computation and Language · Computer Science 2026-02-04 Brian Siyuan Zheng , Alisa Liu , Orevaoghene Ahia , Jonathan Hayase , Yejin Choi , Noah A. Smith

While much of the current research in deep learning-based vulnerability detection relies on disassembled binaries, this paper explores the feasibility of extracting features directly from raw x86-64 machine code. Although assembly language…

Cryptography and Security · Computer Science 2026-01-15 Mitchell Petingola

Trojans are one of the most threatening network attacks currently. HTTP-based Trojan, in particular, accounts for a considerable proportion of them. Moreover, as the network environment becomes more complex, HTTP-based Trojan is more…

Networking and Internet Architecture · Computer Science 2023-09-06 Jiang Xie , Shuhao Li , Yongzheng Zhang , Xiaochun Yun , Jia Li

There is a growing body of literature showing that deep neural networks are vulnerable to adversarial input modification. Recently this work has been extended from image classification to malware classification over boolean features. In…

Machine Learning · Computer Science 2018-06-26 Alex Kouzemtchenko

There is an increasing trend to mine vulnerabilities from software repositories and use machine learning techniques to automatically detect software vulnerabilities. A fundamental but unresolved research question is: how do different…

Software Engineering · Computer Science 2024-06-07 Esma Mouine , Yan Liu , Lu Xiao , Rick Kazman , Xiao Wang