English
Related papers

Related papers: ExploitGym: Can AI Agents Turn Security Vulnerabil…

200 papers

In this paper we argue that a jailbroken GenAI model can cause substantial harm to GenAI-powered applications and facilitate PromptWare, a new type of attack that flips the GenAI model's behavior from serving an application to attacking it.…

Cryptography and Security · Computer Science 2024-08-12 Stav Cohen , Ron Bitton , Ben Nassi

As large language models (LLMs) increasingly integrate native code interpreters, they enable powerful real-time execution capabilities, substantially expanding their utility. However, such integrations introduce potential system-level…

Cryptography and Security · Computer Science 2025-07-28 Gabriel Chua

We present the first comprehensive evaluation of AI agents against human cybersecurity professionals in a live enterprise environment. We evaluate ten cybersecurity professionals alongside six existing AI agents and ARTEMIS, our new agent…

While it is still unclear if agents with Artificial General Intelligence (AGI) could ever be built, we can already use mathematical models to investigate potential safety systems for these agents. We present an AGI safety layer that creates…

Artificial Intelligence · Computer Science 2020-07-13 Koen Holtman

Memory makes LLM-based web agents personalized, powerful, yet exploitable. By storing past interactions to personalize future tasks, agents inadvertently create a persistent attack surface that spans websites and sessions. While existing…

Cryptography and Security · Computer Science 2026-04-08 Wei Zou , Mingwen Dong , Miguel Romero Calvo , Shuaichen Chang , Jiang Guo , Dongkyu Lee , Xing Niu , Xiaofei Ma , Yanjun Qi , Jiarong Jiang

Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…

Cryptography and Security · Computer Science 2026-05-12 Wei Zhao , Zhe Li , Peixin Zhang , Jun Sun

Web applications are prime targets for cyberattacks as gateways to critical services and sensitive data. Traditional penetration testing is costly and expertise-intensive, making it difficult to scale with the growing web ecosystem. While…

Cryptography and Security · Computer Science 2025-10-15 Xiaoxue Ren , Penghao Jiang , Kaixin Li , Zhiyong Huang , Xiaoning Du , Jiaojiao Jiang , Zhenchang Xing , Jiamou Sun , Terry Yue Zhuo

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

Ethical hacking today relies on highly skilled practitioners executing complex sequences of commands, which is inherently time-consuming, difficult to scale, and prone to human error. To help mitigate these limitations, we previously…

Cryptography and Security · Computer Science 2025-07-10 Haitham S. Al-Sinani , Chris J. Mitchell

Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents through tool use, planning, and decision-making abilities, leading to their widespread adoption across diverse tasks. As task complexity grows,…

Multiagent Systems · Computer Science 2025-11-10 Ishan Kavathekar , Hemang Jain , Ameya Rathod , Ponnurangam Kumaraguru , Tanuja Ganu

This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by…

Machine Learning · Computer Science 2026-04-07 Ninghui Li , Kaiyuan Zhang , Kyle Polley , Jerry Ma

We introduce Meta MLGym and MLGym-Bench, a new framework and benchmark for evaluating and developing LLM agents on AI research tasks. This is the first Gym environment for machine learning (ML) tasks, enabling research on reinforcement…

The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active actors capable of executing shell commands, modifying files, calling APIs, and browsing…

Artificial Intelligence · Computer Science 2026-05-19 Ashwin Aravind

Reinforcement learning (RL) has recently shown impressive performance in complex game AI and robotics tasks. To a large extent, this is thanks to the availability of simulated environments such as OpenAI Gym, Atari Learning Environment, or…

Computation and Language · Computer Science 2020-11-18 Rajkumar Ramamurthy , Rafet Sifa , Christian Bauckhage

As the practicality of Artificial Intelligence (AI) and Machine Learning (ML) based techniques grow, there is an ever increasing threat of adversarial attacks. There is a need to red team this ecosystem to identify system vulnerabilities,…

Cryptography and Security · Computer Science 2022-08-17 Chuyen Nguyen , Caleb Morgan , Sudip Mittal

The increasing use of generative Artificial Intelligence (AI) in modern software engineering, particularly Large Language Models (LLMs) for code generation, has transformed professional software development by boosting productivity and…

Software Engineering · Computer Science 2025-07-31 Sabrina Kaniewski , Dieter Holstein , Fabian Schmidt , Tobias Heer

The rise of AI has transformed the software and hardware landscape, enabling powerful capabilities through specialized infrastructures, large-scale data storage, and advanced hardware. However, these innovations introduce unique attack…

Cryptography and Security · Computer Science 2025-08-29 Michael R Smith , Joe Ingram

We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI…

Existing evaluations of AI misuse safeguards provide a patchwork of evidence that is often difficult to connect to real-world decisions. To bridge this gap, we describe an end-to-end argument (a "safety case") that misuse safeguards reduce…

Machine Learning · Computer Science 2025-05-26 Joshua Clymer , Jonah Weinbaum , Robert Kirk , Kimberly Mai , Selena Zhang , Xander Davies

As the industry increasingly adopts agentic AI systems, understanding their unique vulnerabilities becomes critical. Prior research suggests that security flaws at the model level do not fully capture the risks present in agentic…

Artificial Intelligence · Computer Science 2025-09-23 Ilham Wicaksono , Zekun Wu , Rahul Patel , Theo King , Adriano Koshiyama , Philip Treleaven