Related papers: Trace: Unmasking AI Attack Agents Through Terminal…
AI control protocols serve as a defense mechanism to stop untrusted LLM agents from causing harm in autonomous settings. Prior work treats this as a security problem, stress testing with exploits that use the deployment context to subtly…
APT, known as Advanced Persistent Threat, is a difficult challenge for cyber defence. These threats make many traditional defences ineffective as the vulnerabilities exploited by these threats are insiders who have access to and are within…
Recent work has introduced attacks that extract the architecture information of deep neural networks (DNN), as this knowledge enhances an adversary's capability to conduct black-box attacks against the model. This paper presents the first…
Deep learning models for image classification have become standard tools in recent years. A well known vulnerability of these models is their susceptibility to adversarial examples. These are generated by slightly altering an image of a…
Understanding the attack patterns associated with a cyberattack is crucial for comprehending the attacker's behaviors and implementing the right mitigation measures. However, majority of the information regarding new attacks is typically…
This work introduces xOffense, an AI-driven, multi-agent penetration testing framework that shifts the process from labor-intensive, expert-driven manual efforts to fully automated, machine-executable workflows capable of scaling seamlessly…
For the first time, we unveil discernible temporal (or historical) trajectory imprints resulting from adversarial example (AE) attacks. Standing in contrast to existing studies all focusing on spatial (or static) imprints within the…
Sensor systems are extremely popular today and vulnerable to sensor data attacks. Due to possible devastating consequences, counteracting sensor data attacks is an extremely important topic, which has not seen sufficient study. This paper…
The evaluation of Deep Research Agents is a critical challenge, as conventional outcome-based metrics fail to capture the nuances of their complex reasoning. Current evaluation faces two primary challenges: 1) a reliance on singular metrics…
Website fingerprinting (WF) attacks, which covertly monitor user communications to identify the web pages they visit, pose a serious threat to user privacy. Existing WF defenses attempt to reduce attack accuracy by disrupting traffic…
Devices authentication is one crucial aspect of any communication system. Recently, the physical layer approach radio frequency (RF) fingerprinting has gained increased interest as it provides an extra layer of security without requiring…
We empirically evaluate whether AI systems are more effective at attacking or defending in cybersecurity. Using CAI (Cybersecurity AI)'s parallel execution framework, we deployed autonomous agents in 23 Attack/Defense CTF battlegrounds.…
Advanced persistent threat (APT) attacks remain difficult to detect due to their stealth, adaptability, and use of legitimate system components. Provenance-based intrusion detection systems (PIDS) offer a promising defense by capturing…
Command injection and replay attacks are key threats in Cyber Physical Systems (CPS). We develop a novel actuator fingerprinting technique named Time Constant. Time Constant captures the transient dynamics of an actuator and physical…
Many methods have been developed to secure the network infrastructure and communication over the Internet. Intrusion detection is a relatively new addition to such techniques. Intrusion detection systems (IDS) are used to find out if…
Over the past years, literature has shown that attacks exploiting the microarchitecture of modern processors pose a serious threat to the privacy of mobile phone users. This is because applications leave distinct footprints in the…
Audit logs containing system level events are frequently used for behavior modeling as they can provide detailed insight into cyber-threat occurrences. However, mapping low-level system events in audit logs to highlevel behaviors has been a…
High-quality instance and panoptic segmentation has traditionally relied on dense instance-level annotations such as masks, boxes, or points, which are costly, inconsistent, and difficult to scale. Unsupervised and weakly-supervised…
AI-agent guardrails are memoryless: each message is judged in isolation, so an adversary who spreads a single attack across dozens of sessions slips past every session-bound detector because only the aggregate carries the payload. We make…
Effective Cyber Threat Intelligence (CTI) relies upon accurately structured and semantically enriched information extracted from cybersecurity system logs. However, current methodologies often struggle to identify and interpret malicious…