Related papers: Trace: Unmasking AI Attack Agents Through Terminal…
In recent years, the popularity of fingerprint-based biometric authentication systems significantly increased. However, together with many advantages, biometric systems are still vulnerable to presentation attacks (PAs). In particular, this…
AI-driven penetration testing now executes thousands of actions per hour but still lacks the strategic intuition humans apply in competitive security. To build cybersecurity superintelligence --Cybersecurity AI exceeding best human…
Generative search engines and deep research LLM agents promise trustworthy, source-grounded synthesis, yet users regularly encounter overconfidence, weak sourcing, and confusing citation practices. We introduce DeepTRACE, a novel…
The rapid expansion of AI-driven applications powered by large language models has led to a surge in AI interaction data, raising urgent challenges in security, accountability, and risk traceability. This paper presents AiAuditTrack (AAT),…
Several studies have shown that the network traffic that is generated by a visit to a website over Tor reveals information specific to the website through the timing and sizes of network packets. By capturing traffic traces between users…
The need for secure and private Artificial Intelligence (AI) and Machine Learning (ML) on edge and mobile devices has increased the necessity of protecting the architecture of these systems from threats to both security and privacy. With an…
Website Fingerprinting (WF) is a type of traffic analysis attack that enables a local passive eavesdropper to infer the victim's activity, even when the traffic is protected by a VPN or an anonymity system like Tor. Leveraging a…
Active measurements can be used to collect server characteristics on a large scale. This kind of metadata can help discovering hidden relations and commonalities among server deployments offering new possibilities to cluster and classify…
The increasing complexity and frequency of cyber-threats demand intrusion detection systems (IDS) that are not only accurate but also interpretable. This paper presented a novel IDS framework that integrated Explainable Artificial…
Intrusion detection is one of the important mechanisms that provide computer networks security. Due to an increase in attacks and growing dependence upon other fields such as medicine, commerce, and engineering, offering services over a…
Reliable mathematical and scientific reasoning remains an open challenge for large vision-language models. Standard final-answer evaluation often masks reasoning errors, allowing silent failures to persist. To address this gap, we introduce…
As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control (IFC) to provide security guarantees…
Estimating uncertainty for AI agents in real-world multi-turn tool-using interaction with humans is difficult because failures are often triggered by sparse critical episodes (e.g., looping, incoherent tool use, or user-agent…
The vulnerabilities of fingerprint authentication systems have raised security concerns when adapting them to highly secure access-control applications. Therefore, Fingerprint Presentation Attack Detection (FPAD) methods are essential for…
This paper investigates the privacy leakage of smart speakers under an encrypted traffic analysis attack, referred to as voice command fingerprinting. In this attack, an adversary can eavesdrop both outgoing and incoming encrypted voice…
Detecting the source model of AI-generated images is a growing accountability problem. AI fingerprinting techniques address this by detecting imperceptible patterns in the images that are unique to each model, achieving high detection…
Signature-based Intrusion Detection Systems (IDS) detect malicious activities by matching network or host activity against predefined rules. These rules are derived from extensive Cyber Threat Intelligence (CTI), which includes attack…
Recent work shows that deep neural networks are vulnerable to adversarial examples. Much work studies adversarial example generation, while very little work focuses on more critical adversarial defense. Existing adversarial detection…
Object detection models are vulnerable to backdoor attacks, where attackers poison a small subset of training samples by embedding a predefined trigger to manipulate prediction. Detecting poisoned samples (i.e., those containing triggers)…
As multi-agent AI systems are increasingly deployed in real-world settings - from automated customer support to DevOps remediation - failures become harder to diagnose due to cascading effects, hidden dependencies, and long execution…