English
Related papers

Related papers: Using Mechanistic Interpretability to Craft Advers…

200 papers

A popular class of defenses against prompt injection attacks on large language models (LLMs) relies on fine-tuning to separate instructions and data, so that the LLM does not follow instructions that might be present with data. We evaluate…

Cryptography and Security · Computer Science 2025-12-18 Nishit V. Pandya , Andrey Labunets , Sicun Gao , Earlence Fernandes

The literature on adversarial attacks in computer vision typically focuses on pixel-level perturbations. These tend to be very difficult to interpret. Recent work that manipulates the latent representations of image generators to create…

Machine Learning · Computer Science 2023-09-12 Stephen Casper , Max Nadeau , Dylan Hadfield-Menell , Gabriel Kreiman

Deep neural networks are vulnerable to adversarial attacks. White-box adversarial attacks can fool neural networks with small adversarial perturbations, especially for large size images. However, keeping successful adversarial perturbations…

Computer Vision and Pattern Recognition · Computer Science 2020-11-11 Yongwei Wang , Mingquan Feng , Rabab Ward , Z. Jane Wang , Lanjun Wang

Jailbreaks are adversarial attacks designed to bypass the built-in safety mechanisms of large language models. Automated jailbreaks typically optimize an adversarial suffix or adapt long prompt templates by forcing the model to generate the…

Computation and Language · Computer Science 2025-10-31 Raffaele Mura , Giorgio Piras , Kamilė Lukošiūtė , Maura Pintor , Amin Karbasi , Battista Biggio

Deep learning (DL) is becoming popular as a new tool for many applications in wireless communication systems. However, for many classification tasks (e.g., modulation classification) it has been shown that DL-based wireless systems are…

Information Theory · Computer Science 2021-01-29 B. R. Manoj , Meysam Sadeghi , Erik G. Larsson

Safety alignment mechanism are essential for preventing large language models (LLMs) from generating harmful information or unethical content. However, cleverly crafted prompts can bypass these safety measures without accessing the model's…

Computation and Language · Computer Science 2025-01-31 Sunbowen Lee , Shiwen Ni , Chi Wei , Shuaimin Li , Liyang Fan , Ahmadreza Argha , Hamid Alinejad-Rokny , Ruifeng Xu , Yicheng Gong , Min Yang

Large Language Models (LLMs) exhibit remarkable capabilities across a spectrum of tasks in financial services, including report generation, chatbots, sentiment analysis, regulatory compliance, investment advisory, financial knowledge…

Computational Engineering, Finance, and Science · Computer Science 2025-06-02 Hariom Tatsat , Ariye Shater

Current large language models (LLM) provide a strong foundation for large-scale user-oriented natural language tasks. Many users can easily inject adversarial text or instructions through the user interface, thus causing LLM model security…

Computation and Language · Computer Science 2024-11-14 Chong Zhang , Mingyu Jin , Dong Shu , Taowen Wang , Dongfang Liu , Xiaobo Jin

The growing interest for adversarial examples, i.e. maliciously modified examples which fool a classifier, has resulted in many defenses intended to detect them, render them inoffensive or make the model more robust against them. In this…

Machine Learning · Computer Science 2021-03-04 Rémi Bernhard , Pierre-Alain Moellic , Jean-Max Dutertre

Machine Learning (ML) and Deep Learning (DL) models have achieved state-of-the-art performance on multiple learning tasks, from vision to natural language modelling. With the growing adoption of ML and DL to many areas of computer science,…

Machine Learning · Computer Science 2019-06-11 Anshuman Chhabra , Abhishek Roy , Prasant Mohapatra

With the recent advancements in machine learning (ML), numerous ML-based approaches have been extensively applied in software analytics tasks to streamline software development and maintenance processes. Nevertheless, studies indicate that…

Software Engineering · Computer Science 2025-07-15 MD Abdul Awal , Mrigank Rochan , Chanchal K. Roy

White-box Adversarial Example (AE) attacks towards Deep Neural Networks (DNNs) have a more powerful destructive capacity than black-box AE attacks in the fields of AE strategies. However, almost all the white-box approaches lack…

Machine Learning · Computer Science 2021-10-15 Yixiang Wang , Jiqiang Liu , Xiaolin Chang , Jianhua Wang , Ricardo J. Rodríguez

Large Language Models (LLMs) have demonstrated unprecedented capabilities across various natural language processing tasks. Their ability to process and generate viable text and code has made them ubiquitous in many fields, while their…

Machine Learning · Computer Science 2025-05-13 Stef De Sabbata , Stefano Mizzaro , Kevin Roitero

Large Language Models (LLMs) have demonstrated remarkable capabilities across various tasks, yet they remain vulnerable to adversarial manipulations such as jailbreaking via prompt injection attacks. These attacks bypass safety mechanisms…

Machine Learning · Computer Science 2025-07-08 Xin Wei Chia , Swee Liang Wong , Jonathan Pan

Large Language Models (LLMs) have recently demonstrated significant potential in time series forecasting, offering impressive capabilities in handling complex temporal data. However, their robustness and reliability in real-world…

Machine Learning · Computer Science 2025-03-14 Fuqiang Liu , Sicong Jiang , Luis Miranda-Moreno , Seongjin Choi , Lijun Sun

Transformer based large language models with emergent capabilities are becoming increasingly ubiquitous in society. However, the task of understanding and interpreting their internal workings, in the context of adversarial attacks, remains…

Machine Learning · Computer Science 2023-09-04 Varshini Subhash , Anna Bialas , Weiwei Pan , Finale Doshi-Velez

Large Language Models (LLMs) have performed exceptionally in various text-generative tasks, including question answering, translation, code completion, etc. However, the over-assistance of LLMs has raised the challenge of "jailbreaking",…

Cryptography and Security · Computer Science 2024-09-02 Sibo Yi , Yule Liu , Zhen Sun , Tianshuo Cong , Xinlei He , Jiaxing Song , Ke Xu , Qi Li

The black box nature of deep neural networks poses a significant challenge for the deployment of transparent and trustworthy artificial intelligence (AI) systems. With the growing presence of AI in society, it becomes increasingly important…

Machine Learning · Computer Science 2025-11-25 Bianka Kowalska , Halina Kwaśnicka

Adversaries may look to steal or attack black-box NLP systems, either for financial gain or to exploit model errors. One setting of particular interest is machine translation (MT), where models have high commercial value and errors can be…

Computation and Language · Computer Science 2021-01-05 Eric Wallace , Mitchell Stern , Dawn Song

A fundamental issue in deep learning has been adversarial robustness. As these systems have scaled, such issues have persisted. Currently, large language models (LLMs) with billions of parameters suffer from adversarial attacks just like…

Machine Learning · Computer Science 2025-02-11 Brian Formento , Chuan Sheng Foo , See-Kiong Ng