SecureForge: Finding and Preventing Vulnerabilities in LLM-Generated Code Via Prompt Optimization

LLM coding agents now generate code at an unprecedented scale, yet LLM-generated code introduces cybersecurity vulnerabilities into codebases without human involvement. Even when frontier models are explicitly asked to write secure production code with relevant weaknesses to avoid in context, we...

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...

LLM4CodeRE: Generative AI for Code Decompilation Analysis and Reverse Engineering

Code decompilation analysis is a fundamental yet challenging task in malware reverse engineering, particularly due to the pervasive use of sophisticated obfuscation techniques. Although recent large language models LLMs have shown promise in translating low-level representations into high-level...

CacheTrap: Injecting Trojans in LLMs without Leaving Any Traces in Inputs or Weights

Adversarial weight perturbation has emerged as a concerning threat to LLMs that either use training privileges or system-level access to inject adversarial corruption in model weights. With the emergence of innovative defensive solutions that place system- and algorithm-level checks and correctio...

Inside LockBit: Technical, Behavioral, and Financial Anatomy of a Ransomware Empire

LockBit has evolved from an obscure Ransomware-as-a-Service newcomer in 2019 to the most prolific ransomware franchise of 2024. Leveraging a recently leaked MySQL dump of the gang's management panel, this study offers an end-to-end reconstruction of LockBit's technical, behavioral, and financial...

Insecurity through Obscurity: Veiled Vulnerabilities in Closed-Source Contracts

Most blockchains cannot hide the binary code of programs i.e., smart contracts running on them. To conceal proprietary business logic and to potentially deter attacks, many smart contracts are closed-source and employ layers of obfuscation. However, we demonstrate that such obfuscation can obscur...

Red Hat Security Advisory 2026-55757-03

Red Hat Security Advisory 2026-55757-03 - An update for the 389-ds:1.4 module is now available for Red Hat Enterprise Linux 8.4 Advanced Mission Critical Update Support and Red Hat Enterprise Linux 8.4 Extended Update Support Long-Life Add-On. Issues addressed include buffer overflow and null...

Rethinking AI Cloud Infrastructure for Agentic Serving Systems with the Aries Experimentation Framework

Autonomous agents challenge conventional LLM serving by coupling repeated inference with persistent context and sandboxed tool execution. We present Aries, a full-stack experimentation framework that separates task semantics from execution configurations, reconstructs cross-component agent...

Geometric Configurations of Perturbed Jailbreak Prompts

Perturbation techniques that turn unsuccessful jailbreak prompts into successful ones are continuously evolving, constituting a major security threat to LLM safety. In this paper, we investigate the internal representations of such string-level perturbed jailbreak inputs in the small weight model...

DSA Nonce Vulnerabilities: An Interactive Analysis

Digital signatures are fundamental to identity authentication and data integrity in cybersecurity, and the NIST-standardized Digital Signature Algorithm DSA frequently appears in the cryptography track of CTF competitions. However, DSA relies on number theory, modular arithmetic, and large-intege...

From Regression to Prior-Aware Inference: Solving the ILWE Family in Randomness Leakage Attacks against ML-DSA

ML-DSA is a representative lattice-based signature scheme standardized by NIST. It relies on signing randomness and rejection sampling to ensure that released signatures are statistically independent of the secret key. Practical implementations, however, may leak partial information about this...

MRMMIA: Membership Inference Attacks on Memory in Chat Agents

Membership inference attacks MIAs test whether a target data record belongs to a system's private data, and have become a standard tool to measure privacy leakage in machine learning systems. Prior work has primarily focused on training corpora or retrieval databases. However, MIAs against agent...

Longitudinal Analyses of SAST Tools: A CodeQL Case Study

Open-source software OSS pipelines rely on automated static analysis tools to prevent the introduction of vulnerabilities in code. However, there is limited understanding of the efficacy of these tools across the OSS ecosystem over time. In this paper, we introduce a novel method to evaluate stat...

Ghost in the Agent: Redefining Information Flow Tracking for LLM Agents

Autonomous Large Language Model LLM agents are increasingly deployed to conduct complex tasks by interacting with external tools, APIs, and memory stores. However, processing untrusted external data exposes these agents to severe security threats, such as indirect prompt injection and unauthorize...

PISmith: Reinforcement Learning-Based Red Teaming for Prompt Injection Defenses

Prompt injection poses serious security risks to real-world LLM applications, particularly autonomous agents. Although many defenses have been proposed, their robustness against adaptive attacks remains insufficiently evaluated, potentially creating a false sense of security. In this work, we...

Time Will Tell: Large-Scale De-Anonymization of Hidden I2P Services Via Live Behavior Alignment (Extended Version)

I2P Invisible Internet Project is a popular anonymous communication network. While existing de-anonymization methods for I2P focus on identifying potential traffic patterns of target hidden services among extensive network traffic, they often fail to scale effectively across the large and diverse...

Adversarial Sample Generation for Anomaly Detection in Industrial Control Systems

Machine learning ML-based intrusion detection systems IDS are vulnerable to adversarial attacks. It is crucial for an IDS to learn to recognize adversarial examples before malicious entities exploit them. In this paper, we generated adversarial samples using the Jacobian Saliency Map Attack JSMA...

Metabase Authentication Bypass / SQL Injection

Metabase versions x.58.0 through x.63.4 contain an unauthenticated SQL injection vulnerability in the password reset functionality that can allow a remote attacker to manipulate database queries and obtain administrator access. This proof of concept exploits the vulnerable password reset endpoint...

PTSan: A Practical Memory Safety Sanitizer for C/C++ with Pointer-Object Authority

Memory safety errors remain the dominant source of severe vulnerabilities in C and C++. Pointer-based sanitizers provide stronger guarantees than location-based tools such as LLVM's ASan, but their overhead and compatibility limitations have constrained production use. We present PTSan, an LLVM...

ADR: An Agentic Detection System for Enterprise Agentic AI Security

We present the Agentic AI Detection and Response ADR system, the first large-scale, production-proven enterprise framework for securing AI agents operating through the Model Context Protocol MCP. We identify three persistent challenges in this domain: 1 limited observability -- existing Endpoint...

HogVul: Black-Box Adversarial Code Generation Framework against LM-Based Vulnerability Detectors

Recent advances in software vulnerability detection have been driven by Language Model LM-based approaches. However, these models remain vulnerable to adversarial attacks that exploit lexical and syntax perturbations, allowing critical flaws to evade detection. Existing black-box attacks on...

ThinkTrap: Denial-Of-Service Attacks against Black-Box LLM Services Via Infinite Thinking

Large Language Models LLMs have become foundational components in a wide range of applications, including natural language understanding and generation, embodied intelligence, and scientific discovery. As their computational requirements continue to grow, these models are increasingly deployed as...

Securing AI Agents against Prompt Injection Attacks

Retrieval-augmented generation RAG systems have become widely used for enhancing large language model capabilities, but they introduce significant security vulnerabilities through prompt injection attacks. We present a comprehensive benchmark for evaluating prompt injection risks in RAG-enabled A...

The Art of Hide and Seek: Making Pickle-Based Model Supply Chain Poisoning Stealthy Again

Pickle deserialization vulnerabilities have persisted throughout Python's history, remaining widely recognized yet unresolved. Due to its ability to transparently save and restore complex objects into byte streams, many AI/ML frameworks continue to adopt pickle as the model serialization protocol...

BACFuzz: Exposing the Silence on Broken Access Control Vulnerabilities in Web Applications

Broken Access Control BAC remains one of the most critical and widespread vulnerabilities in web applications, allowing attackers to access unauthorized resources or perform privileged actions. Despite its severity, BAC is underexplored in automated testing due to key challenges: the lack of...

Refusal Before Decoding: Detecting and Exploiting Refusal Signals in Intermediate LLM Activations

In this paper, we investigate whether refusal behavior can be predicted from LLM intermediate activations before decoding using linear probes trained on residual stream activations at each transformer block. We find that refusal is linearly decodable well before the final layer, indicating that...

Apple Security Advisory 05-11-2026-1

Apple Security Advisory 05-11-2026-1 - iOS 26.5 and iPadOS 26.5 addresses buffer overflow, bypass, denial of service, information leakage, null pointer, out of bounds access, out of bounds read, out of bounds write, and use-after-free vulnerabilities...

Oracle Poisoning: Corrupting Knowledge Graphs to Weaponise AI Agent Reasoning

We define Oracle Poisoning, an attack class in which an adversary corrupts a structured knowledge graph that AI agents query at runtime via tool-use protocols, causing incorrect conclusions through correct reasoning. Unlike prompt injection, Oracle Poisoning manipulates the data agents reason ove...

SecCodePRM: A Process Reward Model for Code Security

Large Language Models are rapidly becoming core components of modern software development workflows, yet ensuring code security remains challenging. Existing vulnerability detection pipelines either rely on static analyzers or use LLM/GNN-based detectors trained with coarse program-level...

When Handshakes Tell the Truth: Detecting Web Bad Bots Via TLS Fingerprints

Automated traffic continued to surpass human-generated traffic on the web, and a rising proportion of this automation was explicitly malicious. Evasive bots could pretend to be real users, even solve Captchas and mimic human interaction patterns. This work explores a less intrusive, protocol-leve...

LLMs As Firmware Experts: A Runtime-Grown Tree-Of-Agents Framework

Large Language Models LLMs and their agent systems have recently demonstrated strong potential in automating code reasoning and vulnerability detection. However, when applied to large-scale firmware, their performance degrades due to the binary nature of firmware, complex dependency structures, a...

One Signature, Multiple Payments: Demystifying and Detecting Signature Replay Vulnerabilities in Smart Contracts

Smart contracts have significantly advanced blockchain technology, and digital signatures are crucial for reliable verification of contract authority. Through signature verification, smart contracts can ensure that signers possess the required permissions, thus enhancing security and scalability...

Apple Security Advisory 05-12-2025-3

Apple Security Advisory 05-12-2025-3 - macOS Sequoia 15.5 addresses bypass, code execution, double free, information leakage, integer overflow, out of bounds read, and use-after-free vulnerabilities...

CISA: A Tale of Two SOCs - Insights from Two Red Team Assessments

The Cybersecurity and Infrastructure Security Agency CISA conducted simultaneous red team assessments at two organizations and observed different defensive outcomes. In both environments, the red team achieved full domain compromise and accessed sensitive business systems SBSs and cloud resources...

SEVRA-BENCH: Social Engineering of Vulnerabilities in Review Agents

Large language model LLM reviewers are increasingly used in pull-request PR workflows, where their approvals help decide which code is merged into a repository. This raises a question that benchmarks for static vulnerability detection or code generation do not address: can an automated reviewer...

Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models

As Large Language Models evolve for user convenience, vulnerability to jailbreak attacks continues to be reported despite ongoing efforts in safety training. Traditional jailbreak techniques typically focus on a single prompt injection, neglecting the models' ability to remember the flow of...

AgentRFC: Security Design Principles and Conformance Testing for Agent Protocols

AI agent protocols -- including MCP, A2A, ANP, and ACP -- enable autonomous agents to discover capabilities, delegate tasks, and compose services across trust boundaries. Despite massive deployment MCP alone has 97M+ monthly SDK downloads, no systematic security framework for these protocols...

The Attack and Defense Landscape of Agentic AI: A Comprehensive Survey

AI agents that combine large language models with non-AI system components are rapidly emerging in real-world applications, offering unprecedented automation and flexibility. However, this unprecedented flexibility introduces complex security challenges fundamentally different from those in...

Breaking Bad Email Habits: Bounding the Impact of Simulated Phishing Campaigns

Simulated phishing campaigns are widely deployed, yet the behavioral data they produce is endogenous: because training is triggered by clicking, the employees receiving intervention have already demonstrated susceptibility. This endogeneity, combined with the difficulty of separating genuine habi...

Wazuh 4.14.1

Wazuh is a free and open source security platform that unifies XDR and SIEM capabilities. It protects workloads across on-premises, virtualized, containerized, and cloud-based environments. This is the source code release...

Distilling Lightweight Language Models for C/C++ Vulnerabilities

The increasing complexity of modern software systems exacerbates the prevalence of security vulnerabilities, posing risks of severe breaches and substantial economic loss. Consequently, robust code vulnerability detection is essential for software security. While Large Language Models LLMs have...

Spa-VLM: Stealthy Poisoning Attacks on RAG-Based VLM

With the rapid development of the Vision-Language Model VLM, significant progress has been made in Visual Question Answering VQA tasks. However, existing VLM often generate inaccurate answers due to a lack of up-to-date knowledge. To address this issue, recent research has introduced...

CDN Tsunami: Exploiting HTTP/3-HTTP/1.1 Conversion for DoS Attacks

Content Delivery Networks CDNs provide high availability, accelerate content delivery for their host websites, but are also vulnerable to different types of Denial-of-Service DoS attacks. Prior works have studied a variety of DoS attacks with HTTP/1.1 or HTTP/2 connections, but most of them are...

A Structured Cyber Threat Intelligence Dataset Using STIX 2.1 Entities and MITRE ATT&CK Mappings

Cyber threat intelligence CTI reports are typically written in unstructured formats, which complicates the extraction and analysis of important entities and adversarial behaviors. Although existing CTI research provides extraction tools, knowledge-graph frameworks, and MITRE ATT&CK mapped dataset...

Xalgorix Autonomous AI Pentesting Agent 4.5.71

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...

HarmQ: Harmonic Backdoor Attacks against Quantum Neural Networks

Quantum Neural Networks QNNs have emerged as a promising paradigm for quantum machine learning in the Noisy Intermediate-Scale Quantum NISQ era, leveraging quantum phenomena such as superposition and entanglement to process information in exponentially large Hilbert spaces. However, QNNs inherit...

GNSS Spoofing Threat for V2X Communications

Global Navigation Satellite Systems GNSS constitute a core technology for delivering crucial positioning, navigation, and timing PNT services in the Vehicle-to-Everything V2X domain, where they are indispensable for generating Cooperative Awareness Messages CAM that uphold network reliability and...

Code-Augur: Agentic Vulnerability Detection Via Specification Inference

The advent of agentic vulnerability detection is already becoming a watershed moment for software security. Audits conducted entirely by autonomous LLM agents are uncovering critical vulnerabilities in fundamental software underpinning digital society. Many of these vulnerabilities remained maske...

R+R: Reassessing Java Security API Misuse in Current LLMs: A Replication on JCA and JSSE APIs with External Security Knowledge

The misuse of Java security APIs is a serious security problem in software development. Research in 2024 has shown that this problem is widespread in LLM-generated code. However, it remains unclear whether this phenomenon persists in current models and how external security knowledge affects it...

AFL-ICP: Enhancing Industrial Control Protocol Reliability Via Specification-Guided Fuzzing

Industrial Control Protocols ICPs are critical to the reliability and stability of industrial infrastructure, yet their security is fundamentally compromised by a specification-blindness bottleneck. Modern fuzzers, constrained by observation-driven inference, struggle to penetrate deep protocol...