Stateful Cooperative Agents Safeguarding LLMs against Evolving Multi-Turn Attacks

As LLMs become increasingly integrated into complex applications, their vulnerability to adversarial attacks has raised significant concerns. However, existing defenses remain reactive in nature. This limitation makes it difficult for them to counter sophisticated threats, as adversaries...

Formalization of Security

Proof assistants are often used to validate that designs and implementations meet their expected security properties. A further motivation for using proof assistants is to support certification. This chapter focuses on their applications to system security, language-based security, secure...

Deterministic QKD Source Robust against Side-Channel Attacks

Quantum key distribution QKD is secure in principle, but practical security can be undermined by discrepancies between real devices and the idealized models assumed in security proofs. Source side channels, including those exploited by Trojan-horse attacks, are particularly detrimental: neglectin...

Security of World-Model-Based Embodied AI: A Lifecycle of Threats, Defenses, and Evaluation

World models give embodied AI a predictive core: they compress observations into states, simulate action-conditioned futures, and enable planning beyond reactive control. This predictive layer, however, opens a new security boundary-compromise can propagate from data, sensors, prompts, or feedbac...

CoGate: Confidence-Gated Co-Decoding for Secure Code Generation

Large language models are widely used for code generation, but they can also produce insecure programs due to patterns learned from their pretraining data. Decoding-time steering has become an important solution to this problem: a small expert model is combined with the target model at each step ...

angr 9.3.1

angr is an open-source binary analysis platform for Python. It combines both static and dynamic symbolic "concolic" analysis, providing tools to solve a variety of tasks...

From Backlog Items to Security Guidance: Towards Continuous Security Compliance

Continuous software engineering in regulated domains requires engineering teams to address security throughout the development lifecycle. Yet making security requirements explicit in backlog items is still problematic. Engineers must instead infer security relevance of backlog items from brief,...

Targeted Quarantine Strategies Mitigate SIS-Model Cyber Epidemics on Complex Networks

The rapid expansion of highly connected and heterogeneous digital infrastructures has fundamentally altered the dynamics of cyber epidemics, making it increasingly important to understand how malware propagates under realistic structural and policy conditions. In this study, we employ an SIS...

Microsoft SharePoint CVE-2026-50522 Post-Exploitation Payload Collection

A collection of payloads, webshells, and HTTP request artifacts observed following exploitation of the Microsoft SharePoint CVE-2026-50522 vulnerability. The repository documents real-world payloads deployed by multiple threat actors rather than providing an exploit for the underlying vulnerabili...

AgentSnare: Learning to Delay, Divert, and Defuse Autonomous Penetration Agents

Large language model LLM agents automate penetration testing through an observation-action loop, selecting actions based on observations returned by tools. This dependence allows defenders to inject deceptive observations that can mislead the agent's decision-making process. However, existing...

Joern 4.0.590

Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...

When LLM Defenses Backfire: Characterizing Safety, Performance, and Cost Trade-Offs

Jailbreak defenses are essential for protecting large language models LLMs, but they can also introduce secondary costs that weaken model utility. We present a systematic study of these defense trade-offs along three dimensions: performance impact, over-refusal on benign inputs, and inference cos...

Xalgorix Autonomous AI Pentesting Agent 4.5.87

Most scanners detect. Xalgorix proves. An autonomous LLM agent works a full pentest methodology, then an independent verifier re-exploits every finding before it's reported - so you get proof, not a pile of maybes to triage. Self-hosted, private, and bring-your-own-LLM. Built in Go + TypeScript...

ADVERSARIAL: And-Inverter Graph-Assisted Hardware Trojan Detection at Scale

Modern System-on-Chip SoCs often contain hundreds of millions to tens of billions of gates, making existing Hardware Trojan HT detection methods impractical due to their immense scale. The proposed approach incorporates symbolically enabled learning by modeling flattened gate-level netlists as...

LWIS Kernel Driver Out-Of-Bounds Write

The lwis driver provides an interface for writing data to dma-buf objects via the LWISIOENTRYWRITETOBUFFER command. In lwisiobufferwrite, the driver performs a memcpy from a kernel-allocated copy of user data into the kernel mapping of a dma-buf. The driver uses the offset and sizeinbytes fields...

Construction of a Class of Communication-Efficient Quantum Secret Sharing Schemes

Quantum secret sharing is a fundamental technique in quantum cryptography. However, in practical quantum networks, it still faces several bottlenecks, such as high quantum communication cost and low transmission efficiency. To reduce the communication cost, ramp quantum secret sharing schemes hav...

WordPress 5.6+ SkelerSecurity Core Security Plugin REST Batch API Mitigation

This WordPress plugin provides a temporary mitigation for the REST Batch API vulnerability chain commonly referred to as "wp2shell." It requires authentication before requests to the /wp-json/batch/v1 and ?restroute=/batch/v1 endpoints are processed, preventing unauthenticated exploitation of the...

Residual Observability and Attack Detectability in Encrypted OPC UA Traffic

OPC Unified Architecture OPC UA encryption conceals application-layer semantics and restricts intrusion detection to residual communication structure. Although machine learning-based intrusion detection systems IDSs can detect attacks in encrypted OPC UA traffic, the relationship between residual...

A Multi-Model Hybrid Defense Approach against White-Box Adversarial Attacks in Computer Network Traffic

It is crucial to safeguard computer networks from evolving network security threats and unknown cyberattacks. An essential tool for protecting computer networks against unknown cyber threats is Network Intrusion Detection System NIDS. However, NIDS faces a major security concern due to its...

A Non-Intrusive Traffic Analysis Framework for Authorization Risk Detection and Coordinated Response in Web Applications

Authorization violations under valid Web sessions are difficult to identify and handle in real time from traffic because they depend strongly on business semantics and exhibit few distinctive protocol-level features. This paper proposes a non-intrusive traffic analysis framework for authorization...

Security Evaluation of Quantum Distance-Bounding Protocols Via Semidefinite Programming

Quantum distance-bounding QDB protocols let a verifier check that a prover is both genuine and physically nearby. During a timed fast phase of quantum communication, the verifier measures round-trip times to obtain an upper bound on the prover's distance. For a uniform comparison, we isolate the...

Towards Quantum Machine Learning for Assessing the Resilience of Post-Quantum Cryptography

The potential capabilities of quantum computers motivated the development of cryptographic protocols suitable for securing communication against adversaries with access to large fault-tolerant quantum computers. However, even though current quantum computers are limited in terms of size and...

Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation

Reusable skills are becoming a fundamental building block of Large Language Model LLM agents, enabling capabilities to be packaged, shared, and reused across diverse applications. However, existing security research primarily focuses on prompt injection and runtime execution, leaving security ris...

Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation

Penetration testing traditionally evaluates whether adversaries can exploit weaknesses in software, infrastructure, configurations, or operational controls to achieve security-relevant compromise. This paradigm remains necessary for AI-enabled systems, but it is no longer sufficient. In such...

Evaluating Frontier AI Agents As Autonomous Clinical Security Auditors

Clinical AI models can expose patients to harm when adversarial vulnerabilities go undetected, yet formal security auditing requires statistical expertise, specialized tools, and significant time. We present an open evaluation task, built on METR Task Standard v0.3.0, that tests whether frontier ...

BARS: Benign-Anchored Ranking and Selection for False Alarm Reduction in Network Intrusion Detection

False alarms remain a major barrier to deploying network intrusion detection systems NIDS. In high-volume environments, even a sub-1% false positive rate can generate tens of thousands of daily alerts. Filter-based feature selection is attractive because it operates upstream of the classifier and...

When Binaries Talk Back: Representation-Confusion Attacks on LLM-Assisted Reverse Engineering

LLM-assisted reverse-engineering RE systems analyze strings, decompiler output, and tool reports derived from ttacker-controlled binaries. A binary can make data look like instructions or records from one origin look like independent evidence. We call such failures Representation-Confusion Attack...

Trust but Verify? Uncovering the Security Debt of Autonomous Coding Agents

The increasing adoption of autonomous coding agents accelerates software development but also introduces scoped security risks within high-impact file paths that can outpace traditional human review capacity. While prior research has primarily evaluated these systems in terms of functional...

OpenBMC bmcweb Denial of Service / Authentication Bypass

This Metasploit module exploits authentication bypass and denial of service vulnerabilities in bmcweb, the OpenBMC HTTP/Redfish web server that runs on BMC firmware for enterprise servers Intel, IBM, HPE, NVIDIA, and various ODMs...

OpenEMR 7.0.2 Authenticated Arbitrary File Read

This Metasploit auxiliary module targets an authenticated arbitrary file read vulnerability in the Fax/SMS module of OpenEMR version 7.0.2 and related builds...

IPv6 WebSocket Test Server

This script is a minimal, Python WebSocket server that listens on all IPv6 addresses dual-stack enabled on port 8765. It performs the WebSocket handshake, sends a test text message, and responds to connections in separate threads...

Whistleblowersoftware.com Confidentiality Fail

The anonymous reporting flow on whistleblowersoftware.com encrypts report text end-to-end in the browser but does not extend the same guarantee to attachments and exposes the reporter's network identity and timing to a US-based third party. Together these weaken the confidentiality and anonymity...

Asterisk 23.4.1 Security Release

The Asterisk Development Team would like to announce security release Asterisk 23.4.1. It addresses 20 security issues...

Asterisk 22.10.1 Security Release

The Asterisk Development Team would like to announce security release Asterisk 22.10.1. It addresses 20 security issues...

Joern 4.0.573

Joern is the bug hunter's workbench. With this tool, you can uncover attack surface, sloppy coding practices, and variants of known vulnerabilities using an interactive code analysis shell. Joern supports C, C++, LLVM bitcode, x86 binaries via Ghidra, JVM bytecode via Soot, and Javascript...

Agentic and Generative AI for Open-Source Intelligence and Cyber Investigations: Taxonomy, Evaluation, Challenges, and Future Directions

The rapid growth of publicly available digital information has rendered manual open-source intelligence OSINT analysis insufficient for modern intelligence, cybersecurity, and cyber investigation. Large language models LLMs and agentic AI systems, capable of tool use, multi-step reasoning, and...

Apache .htaccess Persistence

This Metasploit module writes a persistence payload into an Apache .htaccess file using modcgi. The .htaccess file itself acts as a CGI shell, executing commands passed via the query string. Inspired by the htshells project by wireghoul...

IPv4/IPv6 Connectivity Validator

This Python script is a network validation utility built with Scapy that performs basic reachability testing for both IPv4 and IPv6 targets using ICMP echo requests...

Knowledge over Parameters: Evolving Smart Contract Vulnerability Detection

Smart contract vulnerabilities are predominantly logic bugs whose detection requires structured, step-by-step procedural knowledge of attack patterns and contract semantics. Existing LLM-based methods struggle to generate this knowledge automatically: prompt-based methods rely on manually crafted...

Understanding Build Reproducibility in the F-Droid Ecosystem

The security of open source applications benefits considerably from the possibility of rebuilding their source and verifying the output. F-Droid, a prominent distribution for open source Android applications, systematically rebuilds them from source and tests their bitwise reproducibility at app...

Trust Boundary Semantic Gaps: A Multi-Dimensional Analysis and Mitigation for Security-By-Design

Modern systems use format-, protocol-, and signature-based mechanisms before accepting artifacts across trust boundaries. These mechanisms are necessary: they show that an artifact is well formed, protocol-compliant, or properly authenticated. They do not, however, show that the artifact satisfie...

CISA: The Journey to Zero Trust

The Journey to Zero Trust is a series of resources on cybersecurity capabilities and architecture topics in support of organizational adoption of modern zero trust principles. Zero trust, with its core concept of never trust and always verify, is the evolution of previous cybersecurity capabiliti...

Cognitive Firewall: A Proactive, Zero-Trust, Multi-Gate Framework for LLM Safety

Large language models LLMs can be induced to produce harmful content through multi turn strategies in which no single user message appears clearly unsafe. Existing runtime safeguards commonly evaluate prompts or responses as isolated messages, which limits their ability to recover ac-cumulated...

CVE-TTP KG: Knowledge Graph Linking Software Vulnerabilities to Attack Behaviors

In the evolving threat landscape, adversaries exploit software vulnerabilities to launch sophisticated attacks, challenging traditional defenses. Although databases like CVE and NVD provide detailed technical information, they often lack links to attacker behaviors such as tactics and techniques,...

FreeBSD Security Advisory - FreeBSD-SA-26:38.jail

FreeBSD Security Advisory - When the JAILATDESC flag is specified, kernjailset and kernjailget released the reference to the caller's current prison before looking up the jail descriptor. If the descriptor lookup failed, error-handling paths released the same reference a second time...

EnclaveX: End-To-End Confidential AI with CPU/GPU TEEs

Large Language Models LLMs have rapidly proliferated, driving widespread adoption of AI applications. Most deployments rely on centralized infrastructures such as Microsoft Azure, Google Cloud, or AWS, requiring users to share sensitive data and training or fine-tuning code. This dependence raise...

An Empirical Study of Security Calibration in Large Language Models for Code

Large Language Models LLMs are rapidly transforming software development, yet their use in security-critical contexts raises a key question: do models know when their generated code is insecure? This property, known as calibration, measures whether a model's confidence aligns with the true...

Robocalls: A Worldwide or US-Only Problem? Analyzing Spam and Fraud in International Phone Calls

Unsolicited automated phone calls robocalls are a serious threat: in the US alone, these calls resulted in reported losses of 1.1$ billion during 2025. Phishing and spoofing consistently rank among the most reported crimes within the FBI's Internet Crime Complaint Center, with phone call scams...

TOR Virtual Network Tunneling Tool 0.4.9.11

Tor is a network of virtual tunnels that allows people and groups to improve their privacy and security on the Internet. It also enables software developers to create new communication tools with built-in privacy features. It provides the foundation for a range of applications that allow...

Maestro 0.17.2

Maestro is a cross-platform desktop app for orchestrating your fleet of AI agents and projects. It's a high-velocity solution for hackers who are juggling multiple projects in parallel. Designed for power users who live on the keyboard and rarely touch the mouse. Collaborate with AI to create...