Related papers: AutoEG: Exploiting Known Third-Party Vulnerabiliti…

Evaluating the security of multi-agent systems (MASs) powered by large language models (LLMs) is challenging, primarily because of the systems' complex internal dynamics and the evolving nature of LLM vulnerabilities. Traditional attack…

Browser agents enable autonomous web interaction but face critical reliability and security challenges in production. This paper presents findings from building and operating a production browser agent. The analysis examines where current…

The increase of IoT devices, driven by advancements in hardware technologies, has led to widespread deployment in large-scale networks that process massive amounts of data daily. However, the reliance on Edge Computing to manage these…

Attack graphs (AG) are used to assess pathways availed by cyber adversaries to penetrate a network. State-of-the-art approaches for AG generation focus mostly on deriving dependencies between system vulnerabilities based on network scans…

Following the enactment of the UN Regulation, substantial efforts have been directed toward implementing intrusion detection and prevention systems (IDPSs) and vulnerability analysis in Controller Area Network (CAN). However, Society of…

Deep Learning has become popular due to its vast applications in almost all domains. However, models trained using deep learning are prone to failure for adversarial samples and carry a considerable risk in sensitive applications. Most of…

Windows malware detectors based on machine learning are vulnerable to adversarial examples, even if the attacker is only given black-box query access to the model. The main drawback of these attacks is that: (i) they are query-inefficient,…

The rapid growth of real-time huge data capturing has pushed the deep learning and data analytic computing to the edge systems. Real-time object recognition on the edge is one of the representative deep neural network (DNN) powered edge…

Web testing has long been recognized as a notoriously difficult task. Even nowadays, web testing still heavily relies on manual efforts while automated web testing is far from achieving human-level performance. Key challenges in web testing…

Safety validation of autonomous driving systems requires high-risk scenario coverage, clear collision semantics, executable trajectories, and attributable multi-vehicle interactions. Existing safety-critical scenario generation methods…

Large Language Models (LLMs), despite advanced general capabilities, still suffer from numerous safety risks, especially jailbreak attacks that bypass safety protocols. Understanding these vulnerabilities through black-box jailbreak…

ChatGPT is a generative pretrained transformer language model created using artificial intelligence implemented as chatbot which can provide very detailed responses to a wide variety of questions. As a very contemporary phenomenon, this…

As a research community, we are still lacking a systematic understanding of the progress on adversarial robustness which often makes it hard to identify the most promising ideas in training robust models. A key challenge in benchmarking…

Computer Use Agents (CUAs), autonomous systems that interact with software interfaces via browsers or virtual machines, are rapidly being deployed in consumer and enterprise environments. These agents introduce novel attack surfaces and…

Automated Vulnerability Repair (AVR) systems, especially those leveraging large language models (LLMs), have demonstrated promising results in patching vulnerabilities -- that is, if we trust their patch validation methodology. Ground-truth…

Current multi-task adversarial text attacks rely on abundant access to shared internal features and numerous queries, often limited to a single task type. As a result, these attacks are less effective against practical scenarios involving…

Existing benchmarks for LLM-based offensive security agents use isolated, single-target setups with a known vulnerable service and fixed objective. They measure exploitation effectively, but miss how real Capture-the-Flag (CTF) participants…

Customers of machine learning systems demand accountability from the companies employing these algorithms for various prediction tasks. Accountability requires understanding of system limit and condition of erroneous predictions, as…

While catastrophic attacks on Ethereum persist, vulnerability research remains fixated on implementation-level smart contract bugs, creating a gap between academic understanding of vulnerabilities and the root causes of high-impact,…

Software vulnerabilities continue to undermine the reliability and security of modern systems, particularly as software complexity outpaces the capabilities of traditional detection methods. This study introduces a genetic algorithm-based…