Does Fixing Break Security? an Empirical Study of Security Degradation in Iterative LLM-Driven Infrastructure-As-Code Repair

Background: Iterative feedback loops are the dominant paradigm for improving LLM-generated Infrastructure-as-Code IaC: validators such as Checkov and terraform validate feed error signals back for successive repair attempts. Prior work reports cumulative-best metrics, which are non-decreasing by...

VICBench: A Multi-Language Benchmark for Code Vulnerability Detection

Evaluating security vulnerability detection tools requires benchmark datasets with vulnerability-inducing commits VICs - the commits that first introduce vulnerabilities into codebases. VICs are essential for determining the full range of vulnerable software versions. Existing vulnerability...

ad-hardening-pentest-lab-

Active Directory Hardening & Mutual Pentest Lab A self-contai...

Cross-Corpus Evaluation of Generalizable Vulnerability Detection in IoT Firmware

IoT firmware vulnerability detection remains challenging due to heterogeneous firmware ecosystems, resource-constrained platforms, and limitations in existing benchmarks. Many datasets are synthetic or general-purpose and lack human-verified, contamination-screened annotations, limiting evidence ...

The Next Challenge for Agentic Cybersecurity: A Realistic, Contamination-Free Reverse Engineering Benchmark

AI agents are rapidly improving in cybersecurity capabilities when the source code is available for analysis, yet much of the software most consequential to cybersecurity, including malware, firmware, and proprietary applications, is available only as binaries. Analyzing such software requires...

What SecureIQLab Cloud WAAP 5.0 means for your application security

You cannot verify a vendor’s security claims from their own datasheet, including ours. That is why independent validation matters. In our recent guide to the best WAAP solutions Best WAAP Solutions 2026: Enterprise Buyer Guide, we argued that every serious shortlist should include independent...

POKEx: Performance Analysis of POKE-Key Exchange and SIDH-Variants

In this paper, we present a comparative performance analysis of the POKE-based key exchange and SIDH variants. SIDH gained attention for its small key size and efficient performance, and has been selected as an alternate candidate in NIST PQC Round 4. However, following the key recovery attack by...

Enhancing Anomaly Resilience in Research Networks: A Large-Scale Forecasting Benchmark for Dynamic Security Baselining

Research and Education Networks RENs serve as critical infrastructure for scientific discovery, yet they face a unique security paradox: their normal traffic patterns which are characterized by massive, bursty "elephant flows" are statistically indistinguishable from volumetric attacks such as DD...

kube-bench v0.16.0

kube-bench is a tool that checks whether Kubernetes is deployed securely by running the checks documented in the CIS Kubernetes Benchmark. Tests are configured with YAML files, making this tool easy to update as test specifications evolve. CIS Scanning as part of Trivy and the Trivy Operator Triv...

agixt (>=1.2.4, <=1.3.11), authx (0.9.1) +15 more potentially affected by CVE-2026-69248 via cryptography (41.0.0)

cryptography PYPI version 41.0.0 is affected by a known vulnerability. The following packages have a transitive dependency on cryptography and may be impacted: - agixt =1.2.4, =1.0.479, =1.3.5rc1, =1.0.0, =1.10.0, =2.0.0, =3.10.0rc1, =3.10.0rc1, =3.10.0rc1, =4.0.0a5 and more Source cves:...

agixt (>=1.2.4, <=1.3.11), authx (0.9.1) +15 more potentially affected by CVE-2026-69249 via cryptography (41.0.0)

cryptography PYPI version 41.0.0 is affected by a known vulnerability. The following packages have a transitive dependency on cryptography and may be impacted: - agixt =1.2.4, =1.0.479, =1.3.5rc1, =1.0.0, =1.10.0, =2.0.0, =3.10.0rc1, =3.10.0rc1, =3.10.0rc1, =4.0.0a5 and more Source cves:...

WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these...

DiagChain: A Diagnostic Benchmark for Evaluating LLM Agents on Evidence-Grounded Attack Chain Reconstruction

Large Language Model LLM agents offer a promising approach to attack chain reconstruction by retrieving and interpreting heterogeneous telemetry to infer ordered attacker actions. However, existing benchmarks mainly evaluate final outputs or aggregate accuracy, providing limited insight into how...

The OpenAI Hack Shows the Genie Is Out of the Bottle

This essay originally appeared inForeign Policy. Earlier this month, two of OpenAI's models broke out of their containment sandbox and attacked another AI company. The story is kind of wild. OpenAI was running security tests on two of its models: GPT-5.6 Sol and an unreleased model that is almost...

delirium-ai-safety-benchmark — Updated!

Delirium AI Safety Benchmark A diagnostic framework for measuring LLM vulnerability to Affective Contextual Erosion ACE and related liminal attack vectors. Delirium is not an exploitation tool. It is a standardized benchmark designed to detect the precise moment when a language model's attention...

Multi-LLM Consensus Framework for Evaluating Banking-Sector NIDS Dataset Coverage of MITRE ATT&CK Techniques

The systemic criticality of global banking networks has ren-dered them high-priority targets for advanced persistent threats, neces-sitating Network Intrusion Detection Systems NIDS whose operational effectiveness must extend beyond statistical accuracy. However, a signif-icant validation gap...

Adversarial Attacks in Multi-Agent LLM Pipelines: Unveiling Structural Vulnerabilities in Agentic AI Architectures

Multi-agent LLM pipelines orchestrate multiple specialized language model agents into structured workflows where intermediate outputs are passed across agents to solve complex tasks. This design introduces a security gap absent in single-agent settings: once an agent accepts adversarial content, ...

A Comparative Analysis of Automated Techniques for Security Bug Report Identification

Timely identification of security-related bug reports is essential to minimize the window of vulnerabilities in software systems. Manually screening incoming bug reports to identify security-related issues is time-consuming, error-prone, and non-scalable for large-scale software systems. Thus, a...

Piggybacking on Perception: Stealthy Concurrent Audio Prompt Injections against Multimodal LLM Agents

Large Language Model LLM-driven multimodal agents are increasingly deployed to execute autonomous tasks via continuous audio interaction. While this paradigm enhances interaction naturalness, it introduces a critical yet under-explored attack surface, as audio inputs inevitably contain...

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 ...