Cybersecurity AI: Evaluating Agentic Cybersecurity in Attack/Defense CTFs

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. Statistical analysis reveals defensive agents achieve 54.3%...

Injection, Attack and Erasure: Revocable Backdoor Attacks Via Machine Unlearning

Backdoor attacks pose a persistent security risk to deep neural networks DNNs due to their stealth and durability. While recent research has explored leveraging model unlearning mechanisms to enhance backdoor concealment, existing attack strategies still leave persistent traces that may be detect...

Are LLMs Reliable Rankers? Rank Manipulation Via Two-Stage Token Optimization

Large language models LLMs are increasingly used as rerankers in information retrieval, yet their ranking behavior can be steered by small, natural-sounding prompts. To expose this vulnerability, we present Rank Anything First RAF, a two-stage token optimization method that crafts concise textual...

Joint-GCG: Unified Gradient-Based Poisoning Attacks on Retrieval-Augmented Generation Systems

Retrieval-Augmented Generation RAG systems enhance Large Language Models LLMs by retrieving relevant documents from external corpora before generating responses. This approach significantly expands LLM capabilities by leveraging vast, up-to-date external knowledge. However, this reliance on...

MLRan: a Behavioural Dataset for Ransomware Analysis and Detection

Ransomware remains a critical threat to cybersecurity, yet publicly available datasets for training machine learning-based ransomware detection models are scarce and often have limited sample size, diversity, and reproducibility. In this paper, we introduce MLRan, a behavioural ransomware dataset...

Apple Security Advisory 08-18-2026-1

Apple Security Advisory 08-18-2026-1 - Safari 26.6.1 addresses out of bounds access and use-after-free vulnerabilities...

MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG

Multimodal agentic retrieval-augmented generation RAG systems expand the attack surface beyond prompt injection to include text poisoning, image injection, direct-query attacks, and orchestrator-level tool manipulation. Existing red-teaming approaches are typically surface-specific and often...

Veritas: A Semantically Grounded Agentic Framework for Memory Corruption Vulnerability Detection in Binaries

Detecting memory corruption vulnerabilities in stripped binaries requires recovering object semantics, interprocedural propagation, and feasible triggers from low-level, lossy representations. Recent LLM-based approaches improve code understanding, but reliable detection still requires grounding ...

VulGD: A LLM-Powered Dynamic Open-Access Vulnerability Graph Database

Software vulnerabilities continue to pose significant threats to modern information systems, requiring a timely and accurate risk assessment. Public repositories, such as the National Vulnerability Database and CVE details, are regularly updated, but predominantly utilize relational data models...

Low Rank Comes with Low Security: Gradient Assembly Poisoning Attacks against Distributed LoRA-Based LLM Systems

Low-Rank Adaptation LoRA has become a popular solution for fine-tuning large language models LLMs in federated settings, dramatically reducing update costs by introducing trainable low-rank matrices. However, when integrated with frameworks like FedIT, LoRA introduces a critical vulnerability:...

Causal-Guided Detoxify Backdoor Attack of Open-Weight LoRA Models

Low-Rank Adaptation LoRA has emerged as an efficient method for fine-tuning large language models LLMs and is widely adopted within the open-source community. However, the decentralized dissemination of LoRA adapters through platforms such as Hugging Face introduces novel security vulnerabilities...

KG-DF: A Black-Box Defense Framework against Jailbreak Attacks Based on Knowledge Graphs

With the widespread application of large language models LLMs in various fields, the security challenges they face have become increasingly prominent, especially the issue of jailbreak. These attacks induce the model to generate erroneous or uncontrolled outputs through crafted inputs, threatenin...

Red Hat Security Advisory 2026-55784-03

Red Hat Security Advisory 2026-55784-03 - An update for unbound is now available for Red Hat Enterprise Linux 8...

TrainShield: Targeted Awareness for Cybersecurity Training

In recent years, cybersecurity threats have increasingly exploited human behaviour rather than purely technical vulnerabilities, exposing the limits of traditional awareness programmes delivered outside real-world contexts. To bridge this gap, we introduce TrainShield, an interaction paradigm for...

Experimental Protocol Fingerprinting in Quantum Networks Via Physical Layer Side Channel Analysis

Quantum communication is a key enabler of next-generation networks, leveraging quantum entanglement to enable a new class of information exchange. While prior work has focused on the theoretical analysis of communication protocols, their exposure to physical layer side channel analysis remains...

Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing

Large language model LLM agents are starting to take on routine work in high-performance computing HPC, including monitoring Slurm jobs, diagnosing failed builds, inspecting simulation output, and coordinating scientific workflows. To do this work, an agent commonly acts under its user's...

Beyond the Syntax: Do Security Experts Trust LLMs for NIDS Rule Engineering?

As network threats evolve, manual NIDS rule engineering has become a critical operational bottleneck. While Large Language Models LLMs show promise for automating this process, their ability to produce production-ready rules remains unvalidated. This paper presents a human-centered investigation...

YellowKey Bitlocker Bypass Mitigation

YellowKey is a zero-day physical attack vulnerability discovered in May 2026 that allows attackers with physical access to completely bypass BitLocker encryption on Windows 11 devices. This is a mitigation that modifies the Windows Recovery Environment to remove or disable the vulnerable...

How Reliable Are AI Attackers against a Fixed Vulnerable Target? A 400-Run Empirical Study of LLM Penetration Testing Consistency

Large language models LLMs can autonomously conduct multi-stage cyber attacks, but the consistency of their offensive behavior under repeated trials remains unstudied. This work presents the first large-scale empirical measurement of LLM attack consistency: 400 autonomous penetration testing runs...

Code-Centric Detection of Vulnerability-Fixing Commits: A Unified Benchmark and Empirical Study

Automated detection of vulnerability-fixing commits VFCs is critical for timely security patch deployment, as advisory databases lag patch releases by a median of 25 days and many fixes never receive advisories. We present a comprehensive evaluation of code language model based VFC detection...

Root-Cause-Driven Automated Vulnerability Repair

Recent LLM-based systems have made automated vulnerability repair increasingly practical, but two challenges remain. First, without strong signals about where a bug originates, repair agents drift toward shallow edits that silence the observed failure while leaving the underlying defect unresolve...

XekRung Technical Report

We present XekRung, a frontier large language model for cybersecurity, designed to provide comprehensive security capabilities. To achieve this, we develop diverse data synthesis pipelines tailored to the cybersecurity domain, enabling the scalable construction of high-quality training data and...

FedPoisonTTP: A Threat Model and Poisoning Attack for Federated Test-Time Personalization

Test-time personalization in federated learning enables models at clients to adjust online to local domain shifts, enhancing robustness and personalization in deployment. Yet, existing federated learning work largely overlooks the security risks that arise when local adaptation occurs at test tim...

Multi-Faceted Attack: Exposing Cross-Model Vulnerabilities in Defense-Equipped Vision-Language Models

The growing misuse of Vision-Language Models VLMs has led providers to deploy multiple safeguards, including alignment tuning, system prompts, and content moderation. However, the real-world robustness of these defenses against adversarial attacks remains underexplored. We introduce Multi-Faceted...

SecRepoBench: Benchmarking LLMs for Secure Code Generation in Real-World Repositories

This paper introduces SecRepoBench, a benchmark to evaluate LLMs on secure code generation in real-world repositories. SecRepoBench has 318 code generation tasks in 27 C/C++ repositories, covering 15 CWEs. We evaluate 19 state-of-the-art LLMs using our benchmark and find that the models struggle...

Behavioral Information Leakage in Darknet Traffic: A Multi-Channel Analysis across Anonymity Networks

Existing darknet traffic classification studies largely emphasize predictive accuracy while offering limited insight into the behavioral mechanisms that make encrypted services distinguishable. This paper proposes a behavioral information leakage framework that decomposes flow-level traffic into...

AI Forensics across White-, Grey-, and Black-Box Access: A Process Model and Research Agenda for Post-Incident Investigation of AI Systems

AI systems are increasingly involved in decisions and actions that may later require investigation. When an AI related incident occurs, investigators need to reconstruct what the system did, why it behaved that way, and which part of the system or supply chain contributed to the outcome. Existing...

AgentAntibody: An Adaptive Immune System for Defending LLM Agents against Prompt Injection

Prompt injection remains a critical threat to LLM agents, yet existing defenses treat each task as a self-contained problem, independent of previous encounters. In practice, user requests are often underspecified: they describe the desired outcome without fully specifying acceptable behavior. An...

Between Safe Boundaries: Exploiting Temporal Consistency for Jailbreaking Text-To-Video Generation Models

Recently, text-to-video T2V models have been widely deployed, sparking growing concerns over their robustness against jailbreak attacks. Existing jailbreak methods, mostly adapted from text-to-image attacks, suffer notable drawbacks when applied to T2V systems. They fail to fully leverage tempora...

AgentRiskBOM: A Risk-Scoping Security Bill of Materials for Agentic AI Systems

Agentic AI systems retrieve private context, invoke tools, write files, call external services, coordinate with other agents, and may act without human approval. Existing bill of materials artifacts improve transparency for dependencies, model metadata, and training provenance, but leave an agent...

CodeQL 2.25.5

Discover vulnerabilities across a codebase with CodeQL, an industry-leading semantic code analysis engine. CodeQL lets you query code as though it were data. Write a query to find all variants of a vulnerability, eradicating it forever. Then share your query to help others do the same...

Stabilising Explainability Fragility in Cybersecurity AI: The Impact and Mitigation of Multicollinearity in Public Benchmark Datasets

This paper investigates a unexplored yet impactful vulnerability in AI explainability used in intrusion detection IDS: multicollinearity-induced instability. Despite extensive reliance on post-hoc explainability tools such as SHAP or LIME, the impact of correlated features on explanation robustne...

Continuous Discovery of Vulnerabilities in LLM Serving Systems with Fuzzing

LLM inference and serving systems have become security-critical infrastructure; however, many of their most concerning failures arise from the serving layer rather than from model behavior alone. Modern inference engines combine KV cache, batching, prefix sharing, speculative decoding, adapters,...

HoneyTrap: Deceiving Large Language Model Attackers to Honeypot Traps with Resilient Multi-Agent Defense

Jailbreak attacks pose significant threats to large language models LLMs, enabling attackers to bypass safeguards. However, existing reactive defense approaches struggle to keep up with the rapidly evolving multi-turn jailbreaks, where attackers continuously deepen their attacks to exploit...

Hyperflex: A SIMD-Based DFA Model for Deep Packet Inspection

Deep Packet Inspection DPI has been extensively employed for network security. It examines traffic payloads by searching for regular expressions regex with the Deterministic Finite Automaton DFA model. However, as the network bandwidth and ruleset size are increasing rapidly, the conventional DFA...

Pack-A-Mal: A Malware Analysis Framework for Open-Source Packages

The increasingly sophisticated environment in which attackers operate makes software security an even greater challenge in open-source projects, where malicious packages are prevalent. Static analysis tools, such as Malcontent, are highly useful but are often incapable of dealing with obfuscated...

Toward Cybersecurity-Expert Small Language Models

Large language models LLMs are transforming everyday applications, yet deployment in cybersecurity lags due to a lack of high-quality, domain-specific models and training datasets. To address this gap, we present CyberPal 2.0, a family of cybersecurity-expert small language models SLMs ranging fr...

FragFake: a Dataset for Fine-Grained Detection of Edited Images with Vision Language Models

Fine-grained edited image detection of localized edits in images is crucial for assessing content authenticity, especially given that modern diffusion models and image editing methods can produce highly realistic manipulations. However, this domain faces three challenges: 1 Binary classifiers yie...

Incident-Data Robustness Analysis of the OWASP Top 10 for LLM Applications (2026): How a Community-Expert Ranking Holds up against a Large-Scale LLM Incident Corpus

The OWASP Top 10 for LLM Applications ranks the risks that a community of security practitioners judges most important. We ask a narrower question: checked against the record of real incidents, does that expert ranking agree with the data? We assembled a large-scale corpus of LLM-security inciden...

Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework

While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption attacks. Adversaries exploit these vulnerabilities by poisoning documents provided by RAG system to manipulate LLM...

Directed Symbolic Execution for Vulnerability Discovery: An LLM-Guided Approach in KLEE

Symbolic execution effectively discovers security violations but suffers from path explosion. Engines like KLEE therefore use path prioritization heuristics to order state exploration, typically optimizing code coverage. However, path prioritization can become trapped in cyclic control-flow...

CARE: Pre-Execution Command Verification for Shell-Executing LLM Agents

Large Language Model LLM agents are increasingly used for coding and terminal automation, making shell-command dispatch a high-stakes runtime control point. We study command-level pre-execution mediation for individual shell commands produced by LLM agents under bounded path context. Existing...

RRAM-DP: Device-Calibrated Differential Privacy for In-Memory Edge Learning

Edge Artificial Intelligence of Things AIoT systems often collect sensitive data in situ, raising serious privacy concerns. Resistive-switching random-access memory RRAM is an attractive substrate for efficient AIoT thanks to its multi-bit storage and compute-in-memory CiM capabilities, while its...

Bit2Watt: A Cyber-Physical Vulnerability Exploiting GPU Workloads across Power and Computing Infrastructures

Modern data centers increasingly rely on large-scale GPU clusters and on-site renewable energy resources, resulting in a tightly coupled cyber-physical system between computing workloads and power-electronic-dominated grids. In this paper, we reveal Bit2Watt, a previously unexplored vulnerability...

The Surface You Test Is Not the Surface That Breaks

Tool-augmented LLM agents are vulnerable to prompt injection: a third party who controls part of the agent's context can plant instructions that the agent then executes as if they came from the user. Current evaluations report a single attack success rate per model on one channel, the tool output...

Silent Consent, Persistent Risk: Android Permission Groups and Custom Permissions

Android's permission system is designed to balance usability with informed consent, yet two legacy mechanisms still undermine that balance in Android 16: i permission groups that silently auto-grant new permissions within a group after a user's initial approval, and ii normal-level custom...

Babel: Jailbreaking Safety Attention Via Obfuscation Distribution Optimized Sampling

Despite rigorous safety alignment, Large Language Models LLMs remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuristic templates or exhaustive trials, lacking mechanistic interpretability and query efficiency. In this study, we investigate an intrinsic...

Forensic Analysis of Video Data Deletion and Recovery in Honeywell Surveillance File System

Real-time video surveillance systems store recorded video using digital video recorders DVRs and network video recorders NVRs. To support continuous high-volume video storage, these devices employ specialized, nonstandard file systems that are often proprietary and undocumented. This lack of...

Aether Smart Contract Security Analysis Framework 5.0.2

Aether is a Python-based framework for analyzing Solidity smart contracts, generating vulnerability findings, producing Foundry-based proof-of-concept PoC tests, and validating exploits on mainnet forks. It combines Solidity AST parsing, taint analysis, control flow graph analysis, cross-contract...

WhatWeb Scanner 0.6.4

WhatWeb is a next-generation web scanner. WhatWeb recognizes web technologies including content management systems CMS, blogging platforms, statistic/analytics packages, JavaScript libraries, web servers, and embedded devices. WhatWeb has over 1800 plugins, each to recognize something different...