Related papers: The Persistent Vulnerability of Aligned AI Systems

We analyzed 3,984 AI agent skills from major marketplaces and found 76 confirmed malicious payloads, including credential theft, backdoor installation, and data exfiltration. 13.4% of all skills contain at least one critical-level security…

Large Language Model (LLM) agents are increasingly proposed to automate offensive security tasks, with recent studies reporting near human-level success rates in Capture-the-Flag (CTF) challenges. We here revisit these results, providing a…

This study examines how Artificial Intelligence can aid in identifying and mitigating cyber threats in the U.S. across four key areas: intrusion detection, malware classification, phishing detection, and insider threat analysis. Each of…

As autonomous AI agents are increasingly deployed in high-stakes environments, ensuring their safety and alignment with human values is becoming a practical deployment concern. Current benchmarks for AI agents primarily evaluate refusal of…

Machine learning-based cybersecurity systems are highly vulnerable to adversarial attacks, while Generative Adversarial Networks (GANs) act as both powerful attack enablers and promising defenses. This survey systematically reviews…

AI agents have the potential to significantly alter the cybersecurity landscape. Here, we introduce the first framework to capture offensive and defensive cyber-capabilities in evolving real-world systems. Instantiating this framework with…

As Large Language Models (LLMs) increasingly become key components in various AI applications, understanding their security vulnerabilities and the effectiveness of defense mechanisms is crucial. This survey examines the security challenges…

Deep learning (DL) has been widely studied for assisting applications of modern wireless communications. One of the applications is automatic modulation classification (AMC). However, DL models are found to be vulnerable to adversarial…

Frontier AI systems are increasingly capable and deployed in high-stakes multi-agent environments. However, existing AI safety benchmarks largely evaluate single agents, leaving multi-agent risks such as coordination failure and conflict…

Adversarial training (AT) is an effective defense for large language models (LLMs) against jailbreak attacks, but performing AT on LLMs is costly. To improve the efficiency of AT for LLMs, recent studies propose continuous AT (CAT) that…

Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, rendering current…

Recent AI systems combine large language models with tools, external knowledge via retrieval-augmented generation (RAG), and even autonomous multi-agent decision loops. This agentic AI paradigm greatly expands capabilities - but also vastly…

Large Language Model (LLM) providers expose fine-tuning APIs that let end users fine-tune their frontier LLMs. Unfortunately, it has been shown that an adversary with fine-tuning access to an LLM can bypass safeguards. Particularly…

AI systems have found a wide range of real-world applications in recent years. The adoption of edge artificial intelligence, embedding AI directly into edge devices, is rapidly growing. Despite the implementation of guardrails and safety…

AI agents have been boosted by large language models. AI agents can function as intelligent assistants and complete tasks on behalf of their users with access to tools and the ability to execute commands in their environments. Through…

Open agentic systems combine LLM-based planning with external capabilities, persistent memory, and privileged execution. They are used in coding assistants, browser copilots, and enterprise automation. OpenClaw is a visible instance of this…

Large Language Models (LLMs) demonstrate complex responses to threat-based manipulations, revealing both vulnerabilities and unexpected performance enhancement opportunities. This study presents a comprehensive analysis of 3,390…

Despite the empirical success in various domains, it has been revealed that deep neural networks are vulnerable to maliciously perturbed input data that much degrade their performance. This is known as adversarial attacks. To counter…

An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and…

Recent research has shown that Large Language Models (LLMs) are vulnerable to automated jailbreak attacks, where adversarial suffixes crafted by algorithms appended to harmful queries bypass safety alignment and trigger unintended…