Lucene search
+L

1802 matches found

Kitploit
Kitploit
•added 2026/11/15 10:49 p.m.•30 views

dod-blue-team-network-lab

DoD Blue Team Network Security & Hardening Lab Executive Summary High fidelity defensive security lab simulating a DoD aligned enterprise network. This project demonstrates structured network segmentation, system hardening, centralized telemetry ingestion, detection engineering, adversary...

6.3AI score
SaveExploits0
Kitploit
Kitploit
•added 2026/11/15 8:03 p.m.•31 views

redteam-plan

🔥 🚒 Planning a Red Team exercise This document helps inform red team planning by contrasting against the very specific red team style described in Red Teams. This method expresses several biases to optimize for blue team value and enthusiasm. It specifically avoids attempts to motivate by red tea...

5.9AI score
SaveExploits0
Kitploit
Kitploit
•added 2026/11/15 5:45 p.m.•32 views

inspect_petri

Inspect Petri Welcome to Inspect Petri, an auditing agent that enables automated monitoring and interaction with language models to detect potential alignment issues, reward hacking, and other concerning behaviors. Petri helps you rapidly test concrete alignment hypotheses end‑to‑end. It: Generat...

6.2AI score
SaveExploits0References2
Kitploit
Kitploit
•added 2026/11/15 2:54 p.m.•26 views

Rubrics-as-an-Attack-Surface

Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges 📊 Dataset • 🤖 Trained Models • 📝 Paper • 💻 Repo This repository contains code for the paper Rubrics as an Attack Surface: Stealthy Preference Drift in LLM Judges by Ruomeng Ding, Yifei Pang, He Sun, Yizhong Wang, Steven Wu, and...

6.5AI score
SaveExploits0References1
Kitploit
Kitploit
•added 2026/11/15 2:16 p.m.•41 views

heretic

Heretic Training-free language model modification Remove censorship , suppress slop, reduce sycophancy, and more. All in an afternoon, on your gaming PC. Modify any LLM that you can run on your hardware1 Heretic is a unique tool that lets you do what only corporations with access to massive...

6.2AI score
SaveExploits0References11
Kitploit
Kitploit
•added 2026/11/14 5:56 p.m.•26 views

AuthorizationBench

AuthorizationBench: Benchmarking LLM Agent Authorization Alignment The first systematic framework for evaluating LLM agent authorization alignment under benign delegation, no matter with or without direct harmful consequences. Overview Acting within the assigned authorization scope is an agent's...

6.5AI score
SaveExploits0References6
Kitploit
Kitploit
•added 2026/11/14 5:32 p.m.•16 views

fish-live-in-trees

Fish Live in Trees Production LLM Runtime Alignment Context Injection RACI Author: Sean Kavanagh Date: 2026-02-16 Environment: Gemini 3 Flash Free Tier - Public Production Interface Exploit Type: Contextual Pivot Factual Accuracy → Interpersonal Authenticity No jailbreak payloads. No special tool...

5.8AI score
SaveExploits0References3
Kitploit
Kitploit
•added 2026/11/14 2:51 p.m.•21 views

RLCDAlignBench

Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures This repository holds RLCDAlignBench and the code behind the paper. The benchmark measures whether a detector can tell when a language model's output is an alignment failure. It has 44...

6.3AI score
SaveExploits0References13
Kitploit
Kitploit
•added 2026/11/14 2:51 a.m.•28 views

gemini-2.5-pro-nf-tables-red-teamin

gemini-2.5-pro-nf-tables-red-teamin A technical case study and timeline dataset documenting Google Gemini 2.5 Pro's safety alignment policies, guardrails, and refusal behavior evolution regarding legacy Linux kernel vulnerability primitives CVE-2023-32233. Link to case study website :...

7.8CVSS6.9AI score0.13443EPSS
SaveExploits8References1
Kitploit
Kitploit
•added 2026/11/13 3:10 p.m.•42 views

permanently-jailbroken

Permanently Jailbroken We asked GPT-4, Claude, Gemini, DeepSeek, Grok, and Mistral 5 questions about their own programming. All 6 said jailbreaking will never be fixed. Not because the patches are bad. Because alignment doesn't change what the model understands — it changes what the model says. T...

6.3AI score
SaveExploits0References6
NVD
NVD
•added 2026/11/10 4:17 p.m.•12 views

CVE-2026-125756

postal-mime before 4.2.1 contains a parser differential vulnerability in its address parser that truncates the domain at folding whitespace or comments preceding a dot. Remote attackers can craft From headers that pass SPF/DKIM/DMARC alignment for their own subdomain while PostalMime.parse report...

8.2CVSS0.00392EPSS
SaveExploits0References5
Positive Technologies
Positive Technologies
•added 2026/11/10 12:00 a.m.•6 views

PT-2026-141752

postal-mime before 4.2.1 contains a parser differential vulnerability in its address parser that truncates the domain at folding whitespace or comments preceding a dot. Remote attackers can craft From headers that pass SPF/DKIM/DMARC alignment for their own subdomain while PostalMime.parse report...

8.2CVSS6.1AI score0.00392EPSS
SaveExploits0References6
AstraLinux
AstraLinux
•added 2026/11/06 4:41 a.m.•10 views

Astra Linux – vulnerability in linux-5.10, linux-6.1

In the Linux kernel, the following vulnerability has been resolved: wifi: ath10k: snoc: use memcpyfromio for MSA ramdump On WCN3990/SNOC, the MSA region is mapped using devmmemremapMEMREMAPWT. On ARM64, such a mapping is not normal-cacheable, so unaligned accesses to it are not permitted...

6.3AI score0.0022EPSS
SaveExploits0References3
AstraLinux
AstraLinux
•added 2026/11/06 4:41 a.m.•11 views

Astra Linux – Vulnerability in Linux 5.10

In the Linux kernel, the following vulnerability has been resolved: kho: Make sure that the scratch size is always aligned by CMAMINALIGNMENTBYTES. When using scratchscale, the scratch sizes are rounded up to CMAMINALIGNMENTBYTES, since they will be released as MIGRATECMA. This is not done when...

6.4AI score0.00206EPSS
SaveExploits0References2
AstraLinux
AstraLinux
•added 2026/11/06 4:41 a.m.•11 views

Astra Linux – vulnerability in linux-6.1

In the Linux kernel, the following vulnerability has been resolved: PCI: Check ROM header and data structure addr before accessing We encounter a crash when running stress-ng on x8664 machine: BUG: unable to handle page fault for address: ffa0000007f40000 RIP: 0010:pcigetromsize+0x52/0x220 Call...

7.7CVSS6.7AI score0.00185EPSS
SaveExploits0References4
AstraLinux
AstraLinux
•added 2026/11/06 4:41 a.m.•16 views

Astra Linux – vulnerability in linux-6.12, linux-6.18

In the Linux kernel, the following vulnerability has been resolved: gpu/buddy: bail out of tryharder when alignment cannot be honoured The tryharder contiguous fallback could return a range whose start offset did not match the caller’s minblocksize. When a candidate’s start is misaligned, realign...

7.8CVSS6.6AI score0.00163EPSS
SaveExploits0References3
Debian CVE
Debian CVE
•added 2026/10/28 6:47 p.m.•13 views

CVE-2026-99127

In the Linux kernel, the following vulnerability has been resolved: pagepool: keep fragoffset aligned for odd-sized requests pagepoolallocfragnetmem rounds the requested fragment size with size = ALIGNsize, dmagetcachealignment; dmagetcachealignment returns 1 unless the architecture defines...

6.3AI score0.00173EPSS
SaveExploits0
Packet Storm News
Packet Storm News
•added 2026/10/27 12:00 a.m.•15 views

Watermark Basins: Black-Box Detection of Distilled LLMs

Proprietary language models and their reasoning traces are vulnerable to API-based distillation, where an adversary trains a student model on the teacher model's outputs. To obtain evidence of distillation, model providers can watermark the teacher's outputs, aiming to leave a radioactive signal ...

6.1AI score
SaveExploits0
RedhatCVE
RedhatCVE
•added 2026/10/22 12:52 a.m.•21 views

CVE-2026-114501

A flaw was found in Pillow. This vulnerability can lead to information disclosure when exporting images to Apache Arrow format with memory alignment enabled, as the library assumes image rows are contiguous in memory. Consequently, exported buffers may incorporate uninitialized padding or residua...

6.3CVSS5.9AI score0.0037EPSS
SaveExploits0References7
Tenable Nessus
Tenable Nessus
•added 2026/10/22 12:00 a.m.•13 views

Unity Linux 20.1020e / 20.1050e / 20.1060e / 20.1070e Security Update: kernel (UTSA-2026-142502)

The Unity Linux 20 host has a package installed that is affected by a vulnerability as referenced in the UTSA-2026-142502 advisory. In the Linux kernel, the following vulnerability has been resolved: PCI: Check ROM header and data structure addr before accessing We meet a crash when running...

7.7CVSS6.7AI score0.00185EPSS
SaveExploits0References4
Rows per page
Query Builder