AI-SPM

Orbyx AI SPM - AI Security Posture Management AI security posture management AI-SPM is a comprehensive approach to maintaining the security and integrity of artificial intelligence AI and machine learning ML systems. It involves continuous monitoring, assessment, and improvement of the security...

ToBAC

🚬 ToBAC NeurIPS 2026 NeurIPS 2026 · Official PyTorch implementation Token by Token, Compromised: Backdoor Vulnerabilities in Unified Autoregressive Models ToBAC Token by Token Backdoor Attack studies how backdoors affect unified autoregressive models that generate both images and text. We...

Hidden Risks of Jev: An Empirical Study of Security, Privacy, and Dual Use

Jev turns natural-language questions into typed answers and probabilities with low latency and cost, enabling applications to route requests and select tools. While this interface allows Jev to integrate naturally into application workflows as a decision layer, the security and privacy implicatio...

SAGE: Similarity-Based Cleaning of Poisoned Training Data from Verified Examples

As machine learning increasingly relies on public, untrusted data sources, data poisoning attacks, which inject malicious examples into training data to induce misclassification of a chosen target, pose a growing threat. Existing defenses either assume zero ground-truth information about which...

VirusCascade: Hijacking Collaborative Reflection in LLM-Powered Recommender Agents

Advancing beyond traditional static scoring models, LLM-powered agentic recommender systems LLM-ARS instantiate users and items as autonomous agents, whose semantic states are dynamically refined through a recurrent process known as collaborative reflection. While this mechanism improves...

Physics-Attested Federated Learning: Securing Collaborative Anomaly Detection in Critical Water Infrastructure

Federated learning enables industrial operators to train shared intrusion detection models without disclosing proprietary operational telemetry. However, existing defenses operate strictly in update space, leaving aggregators blind to data poisoning; model updates derived from fabricated telemetr...

Weaponizing Ground Truth: Data Poisoning Attacks by Exploiting Boundary Misalignment between Antivirus Software and Learning-Based Detectors

Machine-learning ML-based malware detectors are commonly trained using labels obtained from antivirus AV engines and aggregation services e.g., VirusTotal. This practice assumes AV-generated labels provide reliable supervision. However, small byte-level modifications can substantially alter AV...

TraceGuard: Adaptive Multimodal Poison Filtering through Cross-Feature Rank Agreement

Multimodal training relies on image-text corpora collected from external sources, creating opportunities for attackers to poison the data. Stealthy attacks can preserve plausible image-text pairs while concealing the differences used by detectors, so apparently clean data can still redirect the...

CVE-2026-11446

The Booktics – Booking Calendar for Appointments and Service Businesses plugin for WordPress is vulnerable to unauthorized modification of data in all versions up to, and including, 1.0.23. This is due to the createorderpermission permission callback on the POST /wp-json/booktics/v1/orders REST...

CVE-2026-11446: Missing Authorization

The Booktics – Booking Calendar for Appointments and Service Businesses plugin for WordPress is vulnerable to unauthorized modification of data in all versions up to, and including, 1.0.23. This is due to the createorderpermission permission callback on the POST /wp-json/booktics/v1/orders REST...

Empirical Evaluation of Data Poisoning Attacks in Supervised Learning

Data poisoning corrupts training data to degrade a model or to plant attacker-controlled behavior. This study evaluates two representative training-time attacks, label flipping and backdoor poisoning, on MNIST and Fashion-MNIST with three baseline classifiers: Logistic Regression, Linear SVM, and...

MOLE: Detecting Insider Threats in AI Agents

Model misalignment, prompt injection, or operator misuse could lead AI agents operating frontier-lab accounts to exfiltrate model weights, poison training data, or weaken release gates. Existing benchmarks do not test whether defenders can detect this activity among routine work under a limited...

Linux Distros Unpatched Vulnerability : CVE-2026-84366

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - Scrapy is a high-level web crawling and scraping framework for Python. Prior to 2.17.0, in scrapy/core/downloader/handlers/s3.py, Scrapy's S3DownloadHandler...

DEBIAN-CVE-2026-84366

Scrapy is a high-level web crawling and scraping framework for Python. Prior to 2.17.0, in scrapy/core/downloader/handlers/s3.py, Scrapy's S3DownloadHandler converts an S3-scheme bucket and key request into a plaintext HTTP request to the corresponding S3 endpoint unless request.meta"issecure" is...

CVE-2026-84366 Scrapy: S3DownloadHandler sends signed S3 requests over plaintext HTTP by default

Scrapy is a high-level web crawling and scraping framework for Python. Prior to 2.17.0, in scrapy/core/downloader/handlers/s3.py, Scrapy's S3DownloadHandler converts an S3-scheme bucket and key request into a plaintext HTTP request to the corresponding S3 endpoint unless request.meta"issecure" is...

CVE-2026-84366

Scrapy's S3DownloadHandler (in scrapy/core/downloader/handlers/s3.py) converts S3-scheme requests into plaintext HTTP requests to S3 endpoints unless request.meta["is_secure"] is explicitly enabled. Prior to version 2.17.0 , the request is signed and sent in cleartext with the configured AWS cred...

CVE-2026-84366 Scrapy: S3DownloadHandler sends signed S3 requests over plaintext HTTP by default

Scrapy is a high-level web crawling and scraping framework for Python. Prior to 2.17.0, in scrapy/core/downloader/handlers/s3.py, Scrapy's S3DownloadHandler converts an S3-scheme bucket and key request into a plaintext HTTP request to the corresponding S3 endpoint unless request.meta"issecure" is...

CVE-2026-84366

Scrapy is a high-level web crawling and scraping framework for Python. Prior to 2.17.0, in scrapy/core/downloader/handlers/s3.py, Scrapy's S3DownloadHandler converts an S3-scheme bucket and key request into a plaintext HTTP request to the corresponding S3 endpoint unless request.meta"issecure" is...

CVE-2026-84366: Cleartext Transmission of Sensitive Information

Scrapy is a high-level web crawling and scraping framework for Python. Prior to 2.17.0, in scrapy/core/downloader/handlers/s3.py, Scrapy's S3DownloadHandler converts an S3-scheme bucket and key request into a plaintext HTTP request to the corresponding S3 endpoint unless request.meta"issecure" is...

Robustness of Anomaly Detection Models for Industrial Control Systems under Training-Time Data Contamination

Machine-learning-based anomaly detection is increasingly used in industrial control systems ICS, yet most studies assume that detector training data is trustworthy. In practice, training data may be corrupted through compromised logs, labeling errors, manipulated historian records, or unsafe...