English
Related papers

Related papers: Using Mechanistic Interpretability to Craft Advers…

200 papers

Over the past decade, there has been extensive research aimed at enhancing the robustness of neural networks, yet this problem remains vastly unsolved. Here, one major impediment has been the overestimation of the robustness of new defense…

Artificial Intelligence · Computer Science 2023-10-31 Leo Schwinn , David Dobre , Stephan Günnemann , Gauthier Gidel

Methods for adapting language models (LMs) to new tasks and domains have traditionally assumed white-box access to the model, and work by modifying its parameters. However, this is incompatible with a recent trend in the field, where the…

Computation and Language · Computer Science 2023-05-29 Aitor Ormazabal , Mikel Artetxe , Eneko Agirre

Black box models in machine learning have demonstrated excellent predictive performance in complex problems and high-dimensional settings. However, their lack of transparency and interpretability restrict the applicability of such models in…

Machine Learning · Computer Science 2020-06-09 Numair Sani , Jaron Lee , Razieh Nabi , Ilya Shpitser

Large language models (LLMs) are increasingly deployed in settings where inducing a bias toward a certain topic can have significant consequences, and backdoor attacks can be used to produce such models. Prior work on backdoor attacks has…

Cryptography and Security · Computer Science 2026-02-17 Anudeep Das , Prach Chantasantitam , Gurjot Singh , Lipeng He , Mariia Ponomarenko , Florian Kerschbaum

espite being widely used in network intrusion detection systems (NIDSs), machine learning (ML) has proven to be highly vulnerable to adversarial attacks. White-box and black-box adversarial attacks of NIDS have been explored in several…

Cryptography and Security · Computer Science 2024-01-22 Hangsheng Zhang , Dongqi Han , Yinlong Liu , Zhiliang Wang , Jiyan Sun , Shangyuan Zhuang , Jiqiang Liu , Jinsong Dong

Mechanistic interpretability seeks to understand the neural mechanisms that enable specific behaviors in Large Language Models (LLMs) by leveraging causality-based methods. While these approaches have identified neural circuits that copy…

Computation and Language · Computer Science 2023-08-29 Vedant Palit , Rohan Pandey , Aryaman Arora , Paul Pu Liang

Large language models (LLMs) have been serving as effective backbones for retrieval systems, including Retrieval-Augmentation-Generation (RAG), Dense Information Retriever (IR), and Agent Memory Retrieval. Recent studies have demonstrated…

Cryptography and Security · Computer Science 2026-05-18 Jiate Li , Defu Cao , Li Li , Wei Yang , Yuehan Qin , Chenxiao Yu , Tiannuo Yang , Ryan A. Rossi , Yan Liu , Xiyang Hu , Yue Zhao

Large Language Models (LLMs) have achieved significantly advanced capabilities in understanding and generating human language text, which have gained increasing popularity over recent years. Apart from their state-of-the-art natural…

Cryptography and Security · Computer Science 2025-02-11 Yihe Zhou , Tao Ni , Wei-Bin Lee , Qingchuan Zhao

Mechanistic interpretability has revealed how concepts are encoded in large language models (LLMs), but emotional content remains poorly understood at the mechanistic level. We study whether LLMs process emotional valence through dedicated…

Computation and Language · Computer Science 2026-05-08 Sohan Venkatesh

Vulnerability of various machine learning methods to adversarial examples has been recently explored in the literature. Power systems which use these vulnerable methods face a huge threat against adversarial examples. To this end, we first…

Cryptography and Security · Computer Science 2022-02-16 Jiwei Tian , Buhong Wang , Jing Li , Zhen Wang , Mete Ozay

Deep neural networks are vulnerable to adversarial examples that mislead models with imperceptible perturbations. In audio, although adversarial examples have achieved incredible attack success rates on white-box settings and black-box…

Sound · Computer Science 2022-10-13 Deng JiaCheng , Dong Li , Yan Diqun , Wang Rangding , Zeng Jiaming

Understanding why machine learning models behave the way they do empowers both system designers and end-users in many ways: in model selection, feature engineering, in order to trust and act upon the predictions, and in more intuitive user…

Machine Learning · Statistics 2016-06-20 Marco Tulio Ribeiro , Sameer Singh , Carlos Guestrin

While Large Language Models (LLMs) have achieved strong performance across many NLP tasks, their opaque internal mechanisms hinder trustworthiness and safe deployment. Existing surveys in explainable AI largely focus on post-hoc explanation…

Computation and Language · Computer Science 2026-04-21 Yutong Gao , Qinglin Meng , Yuan Zhou , Liangming Pan

We present a novel black-box jailbreaking framework that integrates multiple LLM-as-Attacker strategies to deliver highly transferable and effective attacks. The framework is grounded in three key insights from prior jailbreaking research…

Cryptography and Security · Computer Science 2025-11-07 Yiqi Yang , Hongye Fu

This paper explores the mechanistic interpretability of reinforcement learning (RL) agents through an analysis of a neural network trained on procedural maze environments. By dissecting the network's inner workings, we identified…

Machine Learning · Computer Science 2024-11-05 Tristan Trim , Triston Grayston

Black-box adversarial attacks on Large Vision-Language Models (LVLMs) are challenging due to missing gradients and complex multimodal boundaries. While prior state-of-the-art transfer-based approaches like M-Attack perform well using local…

Machine Learning · Computer Science 2026-02-20 Xiaohan Zhao , Zhaoyi Li , Yaxin Luo , Jiacheng Cui , Zhiqiang Shen

Prompt injection attacks exploit vulnerabilities in large language models (LLMs) to manipulate the model into unintended actions or generate malicious content. As LLM integrated applications gain wider adoption, they face growing…

Cryptography and Security · Computer Science 2024-01-03 Daniel Wankit Yip , Aysan Esmradi , Chun Fai Chan

Safety alignment instills in Large Language Models (LLMs) a critical capacity to refuse malicious requests. Prior works have modeled this refusal mechanism as a single linear direction in the activation space. We posit that this is an…

Cryptography and Security · Computer Science 2025-11-25 Peng Zhang , Peijie Sun

Recent research on reinforcement learning (RL) has suggested that trained agents are vulnerable to maliciously crafted adversarial samples. In this work, we show how such samples can be generalised from White-box and Grey-box attacks to a…

Machine Learning · Computer Science 2019-11-25 Yiren Zhao , Ilia Shumailov , Han Cui , Xitong Gao , Robert Mullins , Ross Anderson

Adversarial attacks on knowledge graph embeddings (KGE) aim to disrupt the model's ability of link prediction by removing or inserting triples. A recent black-box method has attempted to incorporate textual and structural information to…

Computation and Language · Computer Science 2025-10-15 Ting Li , Yang Yang , Yipeng Yu , Liang Yao , Guoqing Chao , Ruifeng Xu