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...

Faction 安全漏洞

Faction is an open-source report generation and evaluation framework developed by Faction Security. Versions of Faction prior to 1.8.3 contained security vulnerabilities. These vulnerabilities stemmed from the lack of output encoding for attachment file names during the evaluation file preview...

UBUNTU-CVE-2026-48844

Roundcube Webmail 1.6.x before 1.6.16 and 1.7.x before 1.7.1 has insecure code evaluation logic in LDAP the autovalues option that could lead to code injection. Support for code evaluation has been removed in 1.6.16 and 1.7.1...

CVE-2026-48844

Roundcube Webmail 1.6.x before 1.6.16 and 1.7.x before 1.7.1 has insecure code evaluation logic in LDAP the autovalues option that could lead to code injection. Support for code evaluation has been removed in 1.6.16 and 1.7.1...

CVE-2026-48844

Roundcube Webmail 1.6.x before 1.6.16 and 1.7.x before 1.7.1 has insecure code evaluation logic in LDAP the autovalues option that could lead to code injection. Support for code evaluation has been removed in 1.6.16 and 1.7.1...

EUVD-2026-31717

Roundcube Webmail 1.6.x before 1.6.16 and 1.7.x before 1.7.1 has insecure code evaluation logic in LDAP the autovalues option that could lead to code injection. Support for code evaluation has been removed in 1.6.16 and 1.7.1...

Malicious code in web-dotenv (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector edd19476eeb1c31707abe6fac6f52dbd1950a0dc25f4854ea5269d6400f8ea37 web-dotenv impersonates the widely-used dotenv package: its package.json copies dotenv's repository git://github.com/motdotla/dotenv.git and homepage...

FuzzPilot: Plateau-Triggered Recipe Validation for Structured Text Fuzzing

FuzzPilot is a controller for AFL++ that moves expensive reasoning out of the mutation hot path. When coverage plateaus, it snapshots the corpus, prepares candidate mutation recipes, evaluates them in short isolated AFL++ micro-campaigns, and promotes only recipes with positive validation reward...

On Reliability of Efficient Membership Inference Vulnerability Evaluation

Membership inference attacks MIAs are popular methods for empirically assessing the leakage of sensitive information in the training data through models or statistics learned from the data. The MIA vulnerability is often evaluated through false positive rate FPR and true positive rate TPR of a...

MAL-2026-4681 Malicious code in tailwind-typography-stylecss (npm)

--- -= Per source details. Do not edit below this line.=- Source: amazon-inspector 273b99f5721643d8ba8335fd73b46b4b32f81406d73f44e7a16552e16b8becd6 Package name 'tailwind-typography-stylecss' impersonates the official '@tailwindcss/typography' plugin; the shipped README is a verbatim copy of the...

PT-2026-43107

Name of the Vulnerable Software and Affected Versions Roundcube Webmail versions 1.6.x through 1.6.15 Roundcube Webmail versions 1.7.x through 1.7.0 Description Insecure code evaluation logic exists within the LDAP autovalues option, which could lead to code injection. Recommendations Update to...

CyBOKClaw: Human-In-The-Loop CyBOK Mapping for Cybersecurity Curriculum

This paper presents CyBOKClaw, an interpretable human-in-the-loop retrieval framework for mapping cybersecurity keywords or phrases KWoPs to the Cyber Security Body of Knowledge CyBOK. Rather than treating the task as strict exact classification, the framework is designed as a top-k candidate...

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...

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...

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...

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...

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...