English
Related papers

Related papers: Language Models Can Autonomously Hack and Self-Rep…

200 papers

Large language models (LLMs) remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry,…

Cryptography and Security · Computer Science 2025-10-28 Pavlos Ntais

This demonstration showcases the integration of a lightweight, locally deployed Large Language Model (LLaMA-3 8b Q-4b) empowered by retrieval augmented generation (RAG) to automate 5G network management, with a strong emphasis on privacy.…

Networking and Internet Architecture · Computer Science 2025-11-27 Ahmadreza Majlesara , Ali Majlesi , Ali Mamaghani , Alireza Shokrani , Babak Hossein Khalaj

If AI models can detect when they are being evaluated, the effectiveness of evaluations might be compromised. For example, models could have systematically different behavior during evaluations, leading to less reliable benchmarks for…

Computation and Language · Computer Science 2025-07-17 Joe Needham , Giles Edkins , Govind Pimpale , Henning Bartsch , Marius Hobbhahn

This study evaluates the ability of GPT-4o to autonomously solve beginner-level offensive security tasks by connecting the model to OverTheWire's Bandit capture-the-flag game. Of the 25 levels that were technically compatible with a…

Cryptography and Security · Computer Science 2026-01-27 Isabelle Bakker , John Hastings

Natural language processing (NLP) tasks, ranging from text classification to text generation, have been revolutionised by the pre-trained language models, such as BERT. This allows corporations to easily build powerful APIs by encapsulating…

Computation and Language · Computer Science 2021-03-19 Xuanli He , Lingjuan Lyu , Qiongkai Xu , Lichao Sun

This paper studies extractable memorization: training data that an adversary can efficiently extract by querying a machine learning model without prior knowledge of the training dataset. We show an adversary can extract gigabytes of…

Adversarial attacks can reliably steer safety-aligned large language models toward unsafe behavior. Empirically, we find that adversarial prompt-injection attacks can amplify attack success rate from the slow polynomial growth observed…

Machine Learning · Computer Science 2026-05-29 Indranil Halder , Annesya Banerjee , Cengiz Pehlevan

Large transformer-based language models dominate modern NLP, yet our understanding of how they encode linguistic information relies primarily on studies of early models like BERT and GPT-2. We systematically probe 25 models from BERT Base…

Computation and Language · Computer Science 2026-04-23 Michael Li , Nishant Subramani

Language model inversion seeks to recover hidden prompts using only language model outputs. This capability has implications for security and accountability in language model deployments, such as leaking private information from an…

Computation and Language · Computer Science 2025-12-12 Murtaza Nazir , Matthew Finlayson , John X. Morris , Xiang Ren , Swabha Swayamdipta

Whether language models possess sentience has no empirical answer. But whether they believe themselves to be sentient can, in principle, be tested. We do so by querying several open-weights models about their own consciousness, and then…

Computation and Language · Computer Science 2026-01-23 Caspar Kaiser , Sean Enderby

We introduce LADDER (Learning through Autonomous Difficulty-Driven Example Recursion), a framework which enables Large Language Models to autonomously improve their problem-solving capabilities through self-guided learning by recursively…

Machine Learning · Computer Science 2025-03-06 Toby Simonds , Akira Yoshiyama

Large language models are highly capable of answering difficult questions by retrieving, recombining, and attending to information in long contexts. For agentic tasks, an additional capability is required: the preservation of an exact state…

Computation and Language · Computer Science 2026-05-19 Tianxiang Dai , Jonathan Fan

Robustness of huge Transformer-based models for natural language processing is an important issue due to their capabilities and wide adoption. One way to understand and improve robustness of these models is an exploration of an adversarial…

Machine learning models deployed as a service (MLaaS) are susceptible to model stealing attacks, where an adversary attempts to steal the model within a restricted access framework. While existing attacks demonstrate near-perfect…

Cryptography and Security · Computer Science 2022-04-26 Sunandini Sanyal , Sravanti Addepalli , R. Venkatesh Babu

LLM agents acting in structured environments fail in operational rather than conversational ways, and reliability depends on procedural knowledge of the environment. Prior self-improvement methods accumulate natural-language guidance…

Artificial Intelligence · Computer Science 2026-05-29 Johannes Moll , Jean-Philippe Corbeil , Jiazhen Pan , Martin Hadamitzky , Daniel Rueckert , Lisa Adams , Keno Bressem

Retrieval-Augmented Generation (RAG) improves pre-trained models by incorporating external knowledge at test time to enable customized adaptation. We study the risk of datastore leakage in Retrieval-In-Context RAG Language Models (LMs). We…

Computation and Language · Computer Science 2024-10-08 Zhenting Qi , Hanlin Zhang , Eric Xing , Sham Kakade , Himabindu Lakkaraju

Large language models (LLMs) are now highly capable at a diverse range of tasks. This paper studies whether or not GPT-4, one such LLM, is capable of assisting researchers in the field of adversarial machine learning. As a case study, we…

Cryptography and Security · Computer Science 2023-07-28 Nicholas Carlini

Software developers frequently hard-code credentials such as passwords, generic secrets, private keys, and generic tokens in software repositories, even though it is strictly advised against due to the severe threat to the security of the…

Cryptography and Security · Computer Science 2025-06-17 Chidera Biringa , Gokhan Kul

Selecting the appropriate model at inference time -- the routing problem -- requires jointly optimizing output quality, cost, latency, and governance constraints. Existing approaches delegate this decision to LLM-based classifiers or…

Networking and Internet Architecture · Computer Science 2026-04-06 Warren Johnson , Charles Lee

Increasing model size has unlocked a dazzling array of capabilities in modern language models. At the same time, even frontier models remain vulnerable to jailbreaks and prompt injections, despite concerted efforts to make them robust. As…

Machine Learning · Computer Science 2025-06-06 Nikolaus Howe , Ian McKenzie , Oskar Hollinsworth , Michał Zajac , Tom Tseng , Aaron Tucker , Pierre-Luc Bacon , Adam Gleave