English
Related papers

Related papers: How Adversarial Environments Mislead Agentic AI?

200 papers

Deepfakes utilise Artificial Intelligence (AI) techniques to create synthetic media where the likeness of one person is replaced with another. There are growing concerns that deepfakes can be maliciously used to create misleading and…

Computer Vision and Pattern Recognition · Computer Science 2022-06-02 Nyee Thoang Lim , Meng Yi Kuan , Muxin Pu , Mei Kuan Lim , Chun Yong Chong

We introduce Advertisement Embedding Attacks (AEA), a new class of LLM security threats that stealthily inject promotional or malicious content into model outputs and AI agents. AEA operate through two low-cost vectors: (1) hijacking…

Cryptography and Security · Computer Science 2025-09-10 Qiming Guo , Jinwen Tang , Xingran Huang

AI agents are autonomous systems that combine LLMs with external tools to solve complex tasks. While such tools extend capability, improper tool permissions introduce security risks such as indirect prompt injection and tool misuse. We…

Cryptography and Security · Computer Science 2026-01-21 Roy Betser , Shamik Bose , Amit Giloni , Chiara Picardi , Sindhu Padakandla , Roman Vainshtein

Numerous safety- or security-critical systems depend on cameras to perceive their surroundings, further allowing artificial intelligence (AI) to analyze the captured images to make important decisions. However, a concerning attack vector…

Cryptography and Security · Computer Science 2024-08-12 Youqian Zhang , Michael Cheung , Chunxi Yang , Xinwei Zhai , Zitong Shen , Xinyu Ji , Eugene Y. Fu , Sze-Yiu Chau , Xiapu Luo

With the rapid evolution of deepfake technologies and the wide dissemination of digital media, personal privacy is facing increasingly serious security threats. Deepfake proactive forensics, which involves embedding imperceptible watermarks…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Lixin Jia , Haiyang Sun , Zhiqing Guo , Yunfeng Diao , Dan Ma , Gaobo Yang

Post-hoc saliency methods are widely used to interpret deep neural networks, but their faithfulness is difficult to evaluate reliably. Existing evaluations mask features according to saliency-induced feature ordering and measure performance…

Machine Learning · Computer Science 2026-05-19 Chia-Ying Hsieh , Hsin-Yuan Fang , Chun-Shu Wei

Traditional models of market efficiency assume that equity prices incorporate information based on content alone, often neglecting the structural influence of reporting timing and cadence. This study introduces the Autonomous Disclosure…

Computational Finance · Quantitative Finance 2026-02-23 Krishna Neupane

This study investigates malicious AI Assistants' manipulative traits and whether the behaviours of malicious AI Assistants can be detected when interacting with human-like simulated users in various decision-making contexts. We also examine…

Cryptography and Security · Computer Science 2025-04-08 Yulu Pi , Ella Bettison , Anna Becker

As autonomous agents become more powerful and widely used, it is becoming increasingly important to ensure they behave safely and stay aligned with system goals, especially in multi-agent settings. Current systems often rely on agents…

Multiagent Systems · Computer Science 2025-04-08 Sagar Tamang , Dibya Jyoti Bora

Contemporary machine learning paradigm excels in statistical data analysis, solving problems that classical AI couldn't. However, it faces key limitations, such as a lack of integration with planning, incomprehensible internal structure,…

Artificial Intelligence · Computer Science 2025-01-29 Zeki Doruk Erden , Boi Faltings

Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack, a class of persistent memory attacks that operates in a more…

Cryptography and Security · Computer Science 2026-05-18 Debeshee Das , Julien Piet , Darya Kaviani , Luca Beurer-Kellner , Florian Tramèr , David Wagner

Embodied artificial intelligence (EAI) integrates advanced AI models into physical entities for real-world interaction. The emergence of foundation models as the "brain" of EAI agents for high-level task planning has shown promising…

Artificial Intelligence · Computer Science 2024-12-02 Zihao Zhu , Bingzhe Wu , Zhengyou Zhang , Lei Han , Qingshan Liu , Baoyuan Wu

The increasing adoption of Reinforcement Learning in safety-critical systems domains such as autonomous vehicles, health, and aviation raises the need for ensuring their safety. Existing safety mechanisms such as adversarial training,…

Machine Learning · Computer Science 2021-11-11 Paulina Stevia Nouwou Mindom , Amin Nikanjam , Foutse Khomh , John Mullins

Data lakehouses run sensitive workloads, where AI-driven automation raises concerns about trust, correctness, and governance. We argue that API-first, programmable lakehouses provide the right abstractions for safe-by-design, agentic…

Artificial Intelligence · Computer Science 2025-10-13 Jacopo Tagliabue , Ciro Greco

Agentic AI represents a paradigm shift in enhancing the capabilities of generative AI models. While these systems demonstrate immense potential and power, current evaluation techniques primarily focus on assessing their efficacy in…

Artificial Intelligence · Computer Science 2025-09-30 Hassen Dhrif

General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse…

Multi-agent, collaborative sensor fusion is a vital component of a multi-national intelligence toolkit. In safety-critical and/or contested environments, adversaries may infiltrate and compromise a number of agents. We analyze state of the…

Robotics · Computer Science 2024-03-26 R. Spencer Hallyburton , Miroslav Pajic

Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…

Artificial Intelligence · Computer Science 2026-04-07 Bowen Wei , Yunbei Zhang , Jinhao Pan , Kai Mei , Xiao Wang , Jihun Hamm , Ziwei Zhu , Yingqiang Ge

Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an…

Cryptography and Security · Computer Science 2026-05-13 Hongwei Yao , Yiming Liu , Yiling He , Bingrun Yang

By providing a standardized interface for LLM agents to interact with external tools, the Model Context Protocol (MCP) is quickly becoming a cornerstone of the modern autonomous agent ecosystem. However, it creates novel attack surfaces due…

Cryptography and Security · Computer Science 2025-08-22 Zhiqiang Wang , Yichao Gao , Yanting Wang , Suyuan Liu , Haifeng Sun , Haoran Cheng , Guanquan Shi , Haohua Du , Xiangyang Li
‹ Prev 1 3 4 5 6 7 10 Next ›