Which Neurons Detect Malicious Code? A Probing Study of LLM Security Knowledge

Background. Large language models LLMs have become increasingly capable of understanding and generating source code, leading to their widespread adoption in software engineering tasks such as code completion, repair, and vulnerability detection. However, despite their strong empirical performance...

Evaluating AI Models' Capability to Automate Voice Phishing Attacks

Voice phishing vishing attacks have traditionally been limited by the need for human operators. The rapid emergence of high-quality AI voice synthesis and large language models LLMs reduces this bottleneck and enables scalable, automated scams. In this paper, we conduct a large-scale survey...

VEXAIoT: Autonomous IoT Vulnerability EXploitation Using AI Agents

Internet of Things IoT systems are inherently vulnerable due to constrained hardware, outdated firmware, and insecure default configurations, creating a need for scalable and adaptive security testing approaches. While recent adoptions of Large Language Model LLM agents have demonstrated promise ...

Using LLMs to Adjudicate Static-Analysis Alerts with Error Reduction Techniques

Static analysis is widely used for finding security weaknesses in source code before deployment, but it often produces far more alerts than analysts can review. We study how well large language models LLMs can adjudicate classify as a real bug or a false alarm static-analysis alerts. We use two...

EUVD-2025-210448

Unauthorized use of Kyocera printers, allows all information stored in the Kyocera address book to be exported. The security measure that encrypts incoming data ian be bypassed with this vulnerability, allowing encrypted data to be decrypted. Passwords and other sensitive information can be...

CVE-2026-57031

Summary of CVE-2026-57031 (Junos OS MX Series): A vulnerability in the packet forwarding engine (PFE) of Juniper Networks Junos OS on MX Series devices allows adjacent subscribers configured on static interfaces to bypass ingress firewall filters, disabling both protocol-level and upstream bandwi...

CVE-2026-59222 Open WebUI: /api/v1/channels/{id}/members exposes full user model including sensitive credentials

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.7.0 before 0.10.0, GET /api/v1/channels//members returned full UserModelResponse objects for channel members, including settings.ui.toolServers.key and webhook configuration, allowing a normal channel...

CVE-2026-59213 Open WebUI: Cross-user model-list exposure via static cache key in get_all_models (aiocache key= vs key_builder= misuse)

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.6.27 before 0.10.0, getallmodels handlers in routers/openai.py and routers/ollama.py passed a lambda to aiocache key instead of keybuilder, causing permission-filtered per-user model lists to share a stat...

CVE-2026-59213

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.6.27 before 0.10.0, getallmodels handlers in routers/openai.py and routers/ollama.py passed a lambda to aiocache key instead of keybuilder, causing permission-filtered per-user model lists to share a stat...

CVE-2026-59213

Open WebUI (self-hosted AI platform) is affected in versions 0.6.27–0.10.0 by a bug in get_all_models handlers (routers/openai.py and routers/ollama.py) where a lambda was passed to aiocache key instead of key_builder. This caused permission-filtered per-user model lists to share a static cache e...

CVE-2026-59213 Open WebUI: Cross-user model-list exposure via static cache key in get_all_models (aiocache key= vs key_builder= misuse)

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.6.27 before 0.10.0, getallmodels handlers in routers/openai.py and routers/ollama.py passed a lambda to aiocache key instead of keybuilder, causing permission-filtered per-user model lists to share a stat...

CVE-2026-59226

Open WebUI is an extensible, feature-rich, and user-friendly self-hosted AI platform. From 0.9.0 before 0.10.0, executeautomation rehydrated automation owners without rechecking that they were still active or still had features.automations, and checkmodelaccess only enforced private-model grants...

PT-2026-56888

Name of the Vulnerable Software and Affected Versions Open WebUI versions 0.8.12 through 0.9.x Description An authenticated non-admin user with read access to an arena wrapper model can access a restricted underlying model. This occurs because task endpoints, such as...

Linux Distros Unpatched Vulnerability : CVE-2026-54499

The Linux/Unix host has one or more packages installed that are impacted by a vulnerability without a vendor supplied patch available. - Stanza is a Stanford NLP Python library for tokenization, sentence segmentation, NER, and parsing of many human languages. Prior to 1.12.2, Stanza model loaders...

PT-2026-56908

Unauthorized use of Kyocera printers, allows all information stored in the Kyocera address book to be exported. The security measure that encrypts incoming data ian be bypassed with this vulnerability, allowing encrypted data to be decrypted. Passwords and other sensitive information can be...

The vulnerability in the script/cgi-bin/app_mgr.cgi of the D-Link DNS-120, DNR-202L, DNS-315L, DNS-320, DNS-320L, DNS-320LW, DNS-321, DNR-322L, DNS-323, DNS-325, DNS-326, DNS-327L, DNR-326, DNS-340L, DNS-343, DNS-345, DNS-726-4, DNS-1100-4, DNS-1200-05, and DNS-1550-04, allows a hacker to execute arbitrary commands.

The vulnerability in the /cgi-bin/appmgr.cgi microprogramming software of D-Link devices such as DNS-120, DNR-202L, DNS-315L, DNS-320, DNS-320L, DNS-320LW, DNS-321, DNR-322L, DNS-323, DNS-325, DNS-326, DNS-327L, DNR-326, DNS-340L, DNS-343, DNS-345, DNS-726-4, DNS-1100-4, DNS-1200-05, and...

The vulnerability in the script /cgi-bin/dsk_mgr.cgi of the D-Link DNS-120, DNR-202L, DNS-315L, DNS-320, DNS-320L, DNS-320LW, DNS-321, DNR-322L, DNS-323, DNS-325, DNS-326, DNS-327L, DNR-326, DNS-340L, DNS-343, DNS-345, DNS-726-4, DNS-1100-4, DNS-1200-05, and DNS-1550-04, allows a hacker to execute arbitrary commands.

The vulnerability of the /cgi-bin/dskmgr.cgi microprogramming software in D-Link devices such as DNS-120, DNR-202L, DNS-315L, DNS-320, DNS-320L, DNS-320LW, DNS-321, DNR-322L, DNS-323, DNS-325, DNS-326, DNS-327L, DNR-326, DNS-340L, DNS-343, DNS-345, DNS-726-4, DNS-1100-4, DNS-1200-05, and...

PT-2026-56830

Name of the Vulnerable Software and Affected Versions Open WebUI versions 0.9.0 through 0.9.x Description The execute automation function rehydrated automation owners without verifying if they remained active or retained features.automations permissions. Additionally, the check model access...

Securing Autonomous Vehicle Systems Via Twin-Aware Federated Reinforcement Learning

Federated reinforcement learning FRL is crucial for enabling collaborative learning across multiple agents without sharing raw data, thereby enhancing privacy and scalability in the decision-making process within dynamic vehicular environments. However, poisoning attacks pose a significant threat...

CVE-2025-63579

Kyocera Command Center RX printers are vulnerable to an unauthorized access flaw that allows an attacker to export all information stored in the Kyocera address book . This vulnerability enables the bypass of security measures intended to encrypt incoming data, allowing for the decryption of sens...