Redefining AI Red Teaming in the Agentic Era: From Weeks to Hours

AI systems are entering critical domains like healthcare, finance, and defense, yet remain vulnerable to adversarial attacks. While AI red teaming is a primary defense, current approaches force operators into manual, library-specific workflows. Operators spend weeks hand-crafting workflows -...

Firmware Distribution As Attack Surface: A Security Study of ASIC Cryptocurrency Miners

ASIC cryptocurrency miners are a core component of blockchain infrastructures, directly converting computation and energy into monetary value. Despite their economic im- portance, their security is rarely evaluated in a structured manner. In this paper, we show that the firmware distribution...

Tailored Prompts, Targeted Protection: Vulnerability-Specific LLM Analysis for Smart Contracts

Smart contracts on blockchains are prone to diverse security vulnerabilities that can lead to significant financial losses due to their immutable nature. Existing detection approaches often lack flexibility across vulnerability types and rely heavily on manually crafted expert rules. In this pape...

The Infinite Mutation Engine? Measuring Polymorphism in LLM-Generated Offensive Code

Malware authors have traditionally relied on polymorphic techniques to produce variants in the same malware family, complicating signature-based detection. Integrating generative AI into offensive toolchains enables attackers to synthesize structurally diverse payloads with identical behavior,...

Lightweight Vulnerability Detection from Code Metrics and Token Features

Vulnerability detection for C/C++ code increasingly relies on heavy representations such as code graphs and deep models, while many practical workflows still benefit from fast and reproducible ranking baselines for human triage. This preprint studies a lightweight function-level vulnerability...

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...

HELO Cryptography: A Lightweight Cryptographic System for Enhancing IoT Security in P2P Data Transmission

The recent surge in security concerns for IoT devices highlights the increasing threat of cryptographic vulnerabilities. These weaknesses can lead to unauthorized access, data breaches, and manipulation of device functions, compromising the privacy and security of both the devices and their users...

ARGUS: Defending LLM Agents against Context-Aware Prompt Injection

The rise of Large Language Model LLM agents, augmented with tool use, skills, and external knowledge, has introduced new security risks. Among them, prompt injection attacks, where adversaries embed malicious instructions into the agent workflow, have emerged as the primary threat. However,...

Rayhunter IMSI Catcher Detector

Rayhunter is a project for detecting IMSI catchers, also known as cell-site simulators or stingrays. It was first designed to run on a cheap mobile hotspot called the Orbic RC400L, but thanks to community efforts, it can support some other devices as well. It's also designed to be as easy to...

GPUBreach: Privilege Escalation Attacks on GPUs Using Rowhammer

NVIDIA GPUs with GDDR memories have been shown susceptible to Rowhammer-based bit-flips, similar to CPUs. However, Rowhammer exploits on GPUs have been limited to injecting untargeted bit-flips in victim data like weights of machine learning models, to degrade model accuracy, unlike CPU exploits...

The Adversarial Discount - AI, Signal Correlation, and the Cybersecurity Arms Race

We study a contest-theoretic model of adversarial investment in which an attacker and a defender allocate resources to AI-augmented capabilities across multiple attack surfaces. The attacker's investment operates through two channels: it amplifies offensive potency unconditionally and erodes...

Joern 4.0.533

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...

sshprank 1.7.0

sshprank is a fast SSH mass-scanner, login cracker, and banner grabber tool using the python-masscan and shodan modules...

DNS Spider Multithreaded Bruteforcer 1.5

DNS Spider is a multi-threaded bruteforcer of subdomains that leverages a wordlist and/or character permutation...

Apache MINA Insecure Deserialization

The Apache MINA project has released versions 2.2.7 and 2.1.12 to address multiple deserialization vulnerabilities...

httpgrep 2.7

httpgrep is a tool written in Python that scans for HTTP servers and finds given strings in HTTP body and HTTP response headers...

PIIGuard: Mitigating PII Harvesting under Adversarial Sanitization

Browsing-enabled LLM assistants can fetch webpages and answer contact-seeking queries, creating a practical channel for scraping contact-style personally identifiable information PII from public pages. Many prior defenses are deployed at the model, service, or agent layer rather than at the webpa...

nimrc 1.0.0

nimrm is a native WinRM interactive shell client written in Nim. It's designed to be a compact and fast tool for system administration and authorized security testing. Key features include NTLM and Kerberos authentication, in-memory operations, file transfers, OPSEC awareness, and cross platform...

Analyzing Unsolicited Internet Traffic: Measuring IoT Security Threats Via Network Telescopes

Network telescopes serve as a critical passive monitoring tool for capturing unsolicited Internet traffic, providing insights into global scanning and reconnaissance behavior. This study analyzes a 10-day dataset during January 2025 consisting of approximately 22 million packets collected by the...

ContextualJailbreak: Evolutionary Red-Teaming Via Simulated Conversational Priming

Large language models LLMs remain vulnerable to jailbreak attacks that bypass safety alignment and elicit harmful responses. A growing body of work shows that contextual priming, where earlier turns covertly bias later replies, constitutes a powerful attack surface, with hand-crafted multi-turn...

FunFuzz: An LLM-Powered Evolutionary Fuzzing Framework

Modern fuzzers increasingly use Large Language Models LLMs to generate structured inputs, but LLM-driven fuzzing is sensitive to prompt initialization and sampling variance, which can reduce exploration efficiency and lead to redundant inputs. We present FunFuzz, a multi-island evolutionary fuzzi...

A Validated Prompt Bank for Malicious Code Generation: Separating Executable Weapons from Security Knowledge in 1,554 Consensus-Labeled Prompts

Existing benchmarks of language-model refusal on malicious-coding tasks routinely conflate requests for executable malicious software with requests for harmful security knowledge. This conflation matters because the two request types plausibly trigger distinct refusal pathways in safety-aligned...

Public Voting Records: A Record, or an Attack Surface?

This is a whitepaper discussing a formal methodology for auditing voter-file disclosure regimes against linkage attacks...

Noisy Networks, Nosy Neighbors: Simple Privacy Attacks against Residential Wireless Traffic

Smart devices, such as light bulbs, TVs, fridges, etc., equipped with computing capabilities and wireless communication, are part of everyday life in many households. Previous work has already shown that a passive eavesdropper can derive private information, household routines, etc., from the...

Autonomous LLM Agent Worms: Cross-Platform Propagation, Automated Discovery and Temporal Re-Entry Defense

Autonomous LLM agents operate as long-running processes with persistent workspaces, memory files, scheduled task state, and messaging integrations. These features create a new propagation risk: attacker-influenced content can be written into persistent agent state, re-enter the LLM decision conte...

HackerSignal: A Large-Scale Multi-Source Dataset Linking Hacker Community Discourse to the CVE Vulnerability Lifecycle

We introduce HackerSignal, a benchmark for temporal out-of-distribution cyber threat intelligence CTI and cross-source CVE linkage. HackerSignal aggregates 7.45 million exact-deduplicated documents from 64 public forum/source identifiers spanning eight source layers and a 36-year window 1990-2026...

LiteShield: Hybrid Feature Selection-Driven Lightweight Intrusion Detection for Resource-Constrained IoT Networks

The rapid expansion of Internet of Things IoT deployments has enlarged the attack surface of modern digital infrastructure while exposing a key security mismatch: many intrusion detection systems IDSs remain too computationally expensive for constrained IoT environments. This paper presents...

Zero Day Attacks: Novel Behaviour or Novel Vulnerability?

Zero-day attacks pose severe cybersecurity risks due to their high success rates and stealth. Because signature-based approaches struggle to detect such attacks, building Intrusion Detection Systems IDSs for detecting zero-day attacks is essential. We contend that for an IDS to be effective it mu...

Joern 4.0.532

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...

Hydra Network Logon Cracker 9.7

THC-Hydra is a high quality parallelized login hacker for Samba, Smbnt, Cisco AAA, FTP, POP3, IMAP, Telnet, HTTP Auth, LDAP, NNTP, MySQL, VNC, ICQ, Socks5, PCNFS, Cisco and more. Includes SSL support, parallel scans, and is part of Nessus...

Reflecthernet: Exfiltrating 100BASE-TX Ethernet Traffic Using a Retroreflector Hardware Trojan

Electromagnetic eavesdropping is a well-established attack vector for remotely monitoring a target activity, most notably displays, over considerable ranges. Other targets have been considered resistant to such attacks or do not exhibit sufficient electromagnetic leakage for practical exploitatio...

Evaluating Retrieval-Augmented Generation for Explainable Malware Analysis

Large Language Models LLMs are increasingly being used as security engineering tools to summarize and explain malware behavior to analysts. A common assumption is that Retrieval-Augmented Generation RAG improves explanation quality by injecting external security knowledge. In this work, we...

Stable Agentic Control: Tool-Mediated LLM Architecture for Autonomous Cyber Defense

Agentic systems involved in high-stake decision-making under adversarial pressure need formal guarantees not offered by existing approaches. Motivated by the operational needs of security operations centers SOCs that must configure endpoint detection and response EDR policies under adversarial...

Evaluating Tabular Representation Learning for Network Intrusion Detection

Classic Network Intrusion Detection Systems NIDS often rely on manual feature engineering to extract meaningful patterns from network traffic data. However, this approach requires domain expertise and runs counter to the widely adopted principle of modern machine learning and neural networks: tha...

Lulzbuster 2.0.0

Lulzbuster is a multithreaded, very fast and smart HTTPS directory and file bruteforcer written in C on top of libcurl. Given a target URL and a wordlist, it enumerates valid paths by firing concurrent HTTP requests and reporting back the responses that look like real hits i.e. status codes the...

Revisiting JBShield: Breaking and Rebuilding Representation-Level Jailbreak Defenses

Defending large language models LLMs against jailbreak attacks, such as Greedy Coordinate Gradient GCG, remains a challenge, particularly under adaptive threat models where an attacker directly targets the defense mechanism. JBShield, a recent jailbreak defense with a 0% attack success rate in so...

Observability for Post-Quantum TLS Readiness: A Multi-Surface Evidence Framework

Post-quantum migration in Transport Layer Security TLS requires evidence-aware measurements that distinguish session negotiation, endpoint capability, certificate-chain evidence, and the provenance of missing observations. This distinction is essential under TLS 1.3 encryption, resumption, mutual...

Trojan Hippo: Weaponizing Agent Memory for Data Exfiltration

Memory systems enable otherwise-stateless LLM agents to persist user information across sessions, but also introduce a new attack surface. We characterize the Trojan Hippo attack, a class of persistent memory attacks that operates in a more realistic threat model than prior memory poisoning work:...

FIRCE: A Framework for Intrusion Response and Conformal Evaluation

Machine learning-based intrusion detection systems deployed in real-world environments frequently suffer from model degradation due to concept drift, where changes in traffic patterns invalidate training assumptions. To address this, we present FIRCE, a Framework for Intrusion Response and...

VulKey: Automated Vulnerability Repair Guided by Domain-Specific Repair Patterns

The increasing prevalence of software vulnerabilities highlights the need for effective Automatic Vulnerability Repair AVR tools. While LLM-based approaches are promising, they struggle to incorporate structured security knowledge from sources like CWE and NVD. Current methods either use this...

CyberAId: AI-Driven Cybersecurity for Financial Service Providers

European financial institutions face mounting regulatory pressure while their security operations centres remain constrained not by data or staffing but by reasoning capacity: enterprise SIEMs cover only a fraction of MITRE ATT&CK techniques, two thirds of SOC teams cannot keep pace with alert...

QASecClaw: A Multi-Agent LLM Approach for False Positive Reduction in Static Application Security Testing

Static Application Security Testing tools help developers find security vulnerabilities before release, but they often produce many false positives. This increases manual review effort, reduces developer trust, and may cause real vulnerabilities to be ignored among noisy reports. We present...

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection

Representation Engineering typically relies on static refusal vectors derived from terminal representations. We move beyond this paradigm, demonstrating that refusal is a dynamic and sparse process rather than a localized outcome. Using Causal Tracing, we uncover the Refusal Trajectory-a persiste...

CodeQL 2.25.3

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...

KingsGuard: Enclave Data Protection under Real-World TEE Vulnerabilities

Trusted Execution Environments TEEs have emerged as a cornerstone for securing sensitive computations by providing isolated enclaves protected from untrusted software. However, their security guarantees are undermined by vulnerabilities in both the enclave code and the underlying hardware design,...

STARE: Step-Wise Temporal Alignment and Red-Teaming Engine for Multi-Modal Toxicity Attack

Red-teaming Vision-Language Models is essential for identifying vulnerabilities where adversarial image-text inputs trigger toxic outputs. Existing approaches treat image generation as a black box, returning only terminal toxicity scores and leaving open the question of when and how toxic semanti...

Phishing Detection in Ethereum Via Temporal Graph Contrastive Learning

Blockchain and decentralized finance have revolutionized the financial ecosystem while simultaneously exposing it to cryptocurrency phishing attacks. Existing phishing detection methods primarily rely on graph learning, but they face significant limitations. Static graph learning approaches fail ...

When RAG Chatbots Expose Their Backend: An Anonymized Case Study of Privacy and Security Risks in Patient-Facing Medical AI

Background: Patient-facing medical chatbots based on retrieval-augmented generation RAG are increasingly promoted to deliver accessible, grounded health information. AI-assisted development lowers the barrier to building them, but they still demand rigorous security, privacy, and governance...

Self-Adaptive Multi-Agent LLM-Based Security Pattern Selection for IoT Systems

The adoption of Internet of Things IoT systems at the network edge of smart architectures is increasing rapidly, intensifying the need for security mechanisms that are both adaptive and resource-efficient. In such environments, runtime defence mechanisms are no longer limited to detection alone b...

Trident: Improving Malware Detection with LLMs and Behavioral Features

Traditionally, machine learning methods for PE malware detection have relied on static features like byte histograms, string information, and PE header contents. One barrier to incorporating dynamic analysis features has been the semi-structured nature of sandbox behavior reports. We show that,...