Related papers: Trace: Unmasking AI Attack Agents Through Terminal…
Due to its crucial role in identity and access management in modern enterprise networks, Active Directory (AD) is a top target of Advanced Persistence Threat (APT) actors. Conventional intrusion detection systems (IDS) excel at identifying…
We present an application of Artificial Intelligence techniques to the field of Information Security. The problem of remote Operating System (OS) Detection, also called OS Fingerprinting, is a crucial step of the penetration testing…
We introduce TRACE, a cross-domain engineering framework for trustworthy agentic AI in operationally critical domains. TRACE combines a four-layer reference architecture with an explicit classical-ML vs. LLM-validator split (L2a/L2b), a…
We present an openly documented methodology for fine-tuning language models to detect temporal attack patterns in multi-agent AI workflows using OpenTelemetry trace analysis. We curate a dataset of 80,851 examples from 18 public…
Model fingerprint detection has shown promise to trace the provenance of AI-generated images in forensic applications. However, despite the inherent adversarial nature of these applications, existing evaluations rarely consider adversarial…
Recent studies have shown that large language models (LLMs) can infer private user attributes (e.g., age, location, gender) from user-generated text shared online, enabling rapid and large-scale privacy breaches. Existing…
AI control protocols use monitors to detect attacks by untrusted AI agents, but standard single-score monitors face two limitations: they miss subtle attacks where outputs look clean but reasoning is off, and they collapse to near-zero…
Fingerprinting refers to the process of identifying underlying Machine Learning (ML) models of AI Systemts, such as Large Language Models (LLMs), by analyzing their unique characteristics or patterns, much like a human fingerprint. The…
Traditional cybersecurity methodologies target deterministic systems and fail to address the probabilistic nature of AI, leaving systems vulnerable to attack vectors such as model inversion, data poisoning, and prompt injection. Recent…
Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…
Control Flow Attestation (CFA) offers a means to detect control flow hijacking attacks on remote devices, enabling verification of their runtime trustworthiness. CFA generates a trace (CFLog) containing the destination of all branching…
We describe a novel approach to monitoring high level behaviors using concepts from AI planning. Our goal is to understand what a program is doing based on its system call trace. This ability is particularly important for detecting malware.…
AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make…
Passive operating system fingerprinting reveals valuable information to the defenders of heterogeneous private networks; at the same time, attackers can use fingerprinting to reconnoiter networks, so defenders need obfuscation techniques to…
Nowadays, every organization might be attacked through its network printers. The malicious exploitation of printing protocols is a dangerous and underestimated threat against every printer today, as highlighted by recent published…
DeepFakes are raising significant social concerns. Although various DeepFake detectors have been developed as forensic countermeasures, these detectors are still vulnerable to attacks. Recently, a few attacks, principally adversarial…
As LLM-based agents increasingly browse the web on users' behalf, a natural question arises: can websites passively identify which underlying model powers an agent? Doing so would represent a significant security risk, enabling targeted…
In Machine Learning as a Service, a provider trains a deep neural network and gives many users access. The hosted (source) model is susceptible to model stealing attacks, where an adversary derives a surrogate model from API access to the…
The Internet has become a prime subject to security attacks and intrusions by attackers. These attacks can lead to system malfunction, network breakdown, data corruption or theft. A network intrusion detection system (IDS) is a tool used…
We argue that trustworthy AI agents, especially in high-stakes and policy-governed domains, should make execution conditional on certified traces rather than rely only on stronger generative models, output-level guardrails, or post-hoc…