English
Related papers

Related papers: Malicious ML Model Detection by Learning Dynamic B…

200 papers

Robust network security systems are essential to prevent and mitigate the harming effects of the ever-growing occurrence of network attacks. In recent years, machine learning-based systems have gain popularity for network security…

Cryptography and Security · Computer Science 2020-03-26 Gonzalo Marín , Pedro Casas , Germán Capdehourat

Current Large Language Models (LLMs), even those tuned for safety and alignment, are susceptible to jailbreaking. Some have found that just further fine-tuning an aligned model with benign data (i.e., data without harmful content)…

Machine Learning · Computer Science 2024-08-21 Luxi He , Mengzhou Xia , Peter Henderson

The growing complexity of Cyber-Physical Systems (CPS) and challenges in ensuring safety and security have led to the increasing use of deep learning methods for accurate and scalable anomaly detection. However, machine learning (ML) models…

Machine Learning · Computer Science 2022-05-04 Xugui Zhou , Maxfield Kouzel , Homa Alemzadeh

A novel approach to malware classification is introduced based on analysis of instruction traces that are collected dynamically from the program in question. The method has been implemented online in a sandbox environment (i.e., a security…

Applications · Statistics 2014-04-10 Curtis Storlie , Blake Anderson , Scott Vander Wiel , Daniel Quist , Curtis Hash , Nathan Brown

While machine learning (ML) models are being increasingly trusted to make decisions in different and varying areas, the safety of systems using such models has become an increasing concern. In particular, ML models are often trained on data…

The state-of-the-art predictive maintenance (PdM) techniques have shown great success in reducing maintenance costs and downtime of complicated machines while increasing overall productivity through extensive utilization of…

Cryptography and Security · Computer Science 2023-08-11 Ayesha Siddique , Ripan Kumar Kundu , Gautam Raj Mode , Khaza Anuarul Hoque

Fine-grained identification of IDS-flagged suspicious traffic is crucial in cybersecurity. In practice, cyber threats evolve continuously, making the discovery of novel malicious traffic a critical necessity as well as the identification of…

Cryptography and Security · Computer Science 2025-11-19 Xiang Luo , Chang Liu , Gang Xiong , Chen Yang , Gaopeng Gou , Yaochen Ren , Zhen Li

Data-poisoning backdoor attacks are serious security threats to machine learning models, where an adversary can manipulate the training dataset to inject backdoors into models. In this paper, we focus on in-training backdoor defense, aiming…

Cryptography and Security · Computer Science 2024-10-16 Shaokui Wei , Hongyuan Zha , Baoyuan Wu

The detection of malicious websites has become a critical issue in cybersecurity. Therefore, this paper offers a comprehensive review of data-driven methods for detecting malicious websites. Traditional approaches and their limitations are…

Cryptography and Security · Computer Science 2023-05-17 Zeyuan Hu , Ziang Yuan

The proliferation of Large Language Models (LLMs) has intensified concerns about manipulative or deceptive behaviors that can undermine user autonomy, trust, and well-being. Existing safety benchmarks predominantly rely on coarse binary…

Artificial Intelligence · Computer Science 2025-12-30 Sadia Asif , Israel Antonio Rosales Laguan , Haris Khan , Shumaila Asif , Muneeb Asif

Large Language Models (LLMs) have been shown to be susceptible to jailbreak attacks, or adversarial attacks used to illicit high risk behavior from a model. Jailbreaks have been exploited by cybercriminals and blackhat actors to cause…

Computation and Language · Computer Science 2025-01-07 Joao Fonseca , Andrew Bell , Julia Stoyanovich

Black-box finetuning is an emerging interface for adapting state-of-the-art language models to user needs. However, such access may also let malicious actors undermine model safety. To demonstrate the challenge of defending finetuning…

Cryptography and Security · Computer Science 2024-07-01 Danny Halawi , Alexander Wei , Eric Wallace , Tony T. Wang , Nika Haghtalab , Jacob Steinhardt

Detecting and intercepting malicious requests are one of the most widely used ways against attacks in the network security. Most existing detecting approaches, including matching blacklist characters and machine learning algorithms have all…

Machine Learning · Computer Science 2020-11-13 Wenhao Li , Bincheng Zhang , Jiajie Zhang

Malicious URL, a.k.a. malicious website, is a common and serious threat to cybersecurity. Malicious URLs host unsolicited content (spam, phishing, drive-by exploits, etc.) and lure unsuspecting users to become victims of scams (monetary…

Machine Learning · Computer Science 2019-08-22 Doyen Sahoo , Chenghao Liu , Steven C. H. Hoi

According to Gartner, more than 70% of organizations will have integrated AI models into their workflows by the end of 2025. In order to reduce cost and foster innovation, it is often the case that pre-trained models are fetched from model…

Cryptography and Security · Computer Science 2026-01-09 Mohamed Nabeel , Oleksii Starov

Large-scale pre-trained models (PTMs) such as BERT and GPT have achieved great success in diverse fields. The typical paradigm is to pre-train a big deep learning model on large-scale data sets, and then fine-tune the model on small…

Cryptography and Security · Computer Science 2024-05-08 Minghang Deng , Zhong Zhang , Junming Shao

Despite the strong multimodal performance, large vision-language models (LVLMs) are vulnerable during fine-tuning to backdoor attacks, where adversaries insert trigger-embedded samples into the training data to implant behaviors that can be…

Computer Vision and Pattern Recognition · Computer Science 2026-03-16 Zhifang Zhang , Bojun Yang , Shuo He , Weitong Chen , Wei Emma Zhang , Olaf Maennel , Lei Feng , Miao Xu

Malicious URLs pose significant security risks as they facilitate phishing attacks, distribute malware, and empower attackers to deface websites. Blacklist detection methods fail to identify new or obfuscated URLs because they depend on…

Cryptography and Security · Computer Science 2025-10-21 Md. Ifthekhar Hossain , Kazi Abdullah Al Arafat , Bryce Shepard , Kayd Craig , Imtiaz Parvez

With the integration of an additional modality, large vision-language models (LVLMs) exhibit greater vulnerability to safety risks (e.g., jailbreaking) compared to their language-only predecessors. Although recent studies have devoted…

Machine Learning · Computer Science 2025-01-07 Ziwei Zheng , Junyao Zhao , Le Yang , Lijun He , Fan Li

Context: Open-source Pre-Trained Models (PTMs) provide extensive resources for various Machine Learning (ML) tasks, yet these resources lack a classification tailored to Software Engineering (SE) needs to support the reliable identification…

Software Engineering · Computer Science 2025-12-04 Alexandra González , Xavier Franch , David Lo , Silverio Martínez-Fernández