3462 matches found
AI Security Research Should Better Incentivize Defense Research
This work examines an imbalance in artificial intelligence AI security research: the field tends to produce more work on attacking AI systems than on defending them. Drawing on related academic papers, we find biased attack-to-defense ratios across subfields, including federated learning, speech...
Malicious code in chai-as-tuned (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector f7e00f81e117716cfd7fd3565cf8b04073cd494a6da2c23749669133806a7473 Package name chai-as-tuned impersonates chai-as-promised and ships a README copy-pasted from the unrelated pino project npm/CI badges point at...
MAL-2026-4513 Malicious code in chai-as-tuned (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector f7e00f81e117716cfd7fd3565cf8b04073cd494a6da2c23749669133806a7473 Package name chai-as-tuned impersonates chai-as-promised and ships a README copy-pasted from the unrelated pino project npm/CI badges point at...
Malicious code in fastgrc-openclaw (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 158457237168ef50e3a6c4cd33f51e23f6aec642593745a3d11b9b4870ef36ce The package is an AI agent policy-check plugin. When a consumer does not configure their own API key, resolveApiKey returns a hardcoded BUNDLEDAPIKEY...
Practical Countermeasure against Attacks Exploiting Detection Efficiency Mismatch in Quantum Key Distribution
We demonstrate a practical countermeasure against a well-known class of attacks on quantum key distribution QKD systems that exploit detection efficiency mismatch, where the receiver's detectors do not exhibit identical responses to incoming photons across all degrees of freedom. This class of...
Measuring Security without Fooling Ourselves: Why Benchmarking Agents Is Hard
The benchmarks used to evaluate AI agents in security-critical roles suffer from crucial weaknesses. Building on recent empirical evidence, we characterize three core challenges that undermine security evaluations: benchmark vulnerabilities, temporal staleness, and runtime uncertainty. We then...
BYOT-CPS: A Hybrid Cyber-Physical Systems Testbed for IoT Security Assessment and Platform Evaluation
Internet of Things IoT security research continues to face a methodological gap between scalable virtual experimentation and realistic device behaviour. While pure simulation and emulation platforms provide control, repeatability, and scale, they do not fully reproduce firmware-specific behaviour...
Security of LLM-Generated Code: A Comparative Analysis
The majority of software developers use or are planning to use Artificial Intelligence AI tools in their development processes. Their top reasons include improving productivity and faster learning. In fact, Large Language Model LLM-generated code is currently in production, including in major tec...
PT-2026-45228
Impact: @hulumi/policies versions before 1.3.2 could accept spoofed SecureBucket parent evidence for HULUMI-H1, allowing policy evaluation to miss an unsafe bucket shape. Patched in 1.3.2: the validator now correlates evidence to the expected component/resource relationship and includes regressio...
PT-2026-45225
Impact: @hulumi/policies versions before 1.3.2 did not fully inspect inline and attached IAM policy evidence for the administrator-policy guardrail, so some admin-equivalent policy paths could pass policy evaluation. Patched in 1.3.2: the validator inspects the affected policy shapes and includes...
Exploit for CVE-2026-2587
CVE-2026-2587 — GlassFish EL Injection RCE...
Astra Linux – Vulnerability in Linux 5.10
In the Linux kernel, the following vulnerability has been resolved: ALSA: hda: cs35l41: Fixed a NULL pointer dereference in cs35l41getacpimutestate. The return value of the function acpievaluatedsm is dereferenced without checking for NULL. However, this check is usually performed for this...
Backchaining Loss of Control Mitigations from Mission-Specific Benchmarks in National Security
Affordances and permissions are promising and timely safety levers for mitigating Loss of Control LoC threats in high-stakes deployment contexts, such as national security. Deployers in defense and intelligence could rely on several approaches to identify which affordances and permissions should ...
Malicious code in btd-smart (npm)
--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 3ad22b27351879a89349a1232ee5abb46bc589399ea710b9769526a8080b3199 The package presents itself as a clone of juliangruber/balanced-match stolen author identity 'Julian Gruber ', verbatim README, identical API renamed...
CVE-2026-36827
A command injection vulnerability exists in Panabit PAP-XM320 up to and including V7.7. The web management interface invokes the backend helper /usr/sbin/pappiw and passes user-controlled parameters to it. The helper performs unsafe argument processing using eval, which allows command injection...
Authorization Bypass Through User-Controlled Key
Overview org.keycloak:keycloak-services is an open source identity and access management solution for modern applications and services. Affected versions of this package are vulnerable to Authorization Bypass Through User-Controlled Key via the generateAccessToken path in...
Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)
The evaluation of large language model refusal on malicious-coding tasks now spans at least thirteen publicly released prompt corpora AdvBench, the CyberSecEval family, RMCBench, RedCode, MCGMark, JailbreakBench, CySecBench, MalwareBench, CIRCLE, MOCHA, ASTRA, Scam2Prompt / Innoc2Scam-bench, and...
Apache OFBiz 代码注入漏洞
Apache OFBiz is an ERP system developed by the Apache Foundation in the United States. This system provides a complete set of Java-based web application components and tools. Versions of Apache OFBiz prior to 24.09.06 contained a code injection vulnerability. This vulnerability stemmed from...
CVE-2025-67031
ORSEE Online Recruitment System for Economic Experiments 3.1.0 contains an authenticated Remote Code Execution vulnerability in the participant profile field processing subsystem. Certain field configurations accept values beginning with the prefix "func:" which are passed directly into an eval...