heretic

Heretic: Fully automatic censorship removal for language models Heretic is a tool that removes censorship aka "safety alignment" from transformer-based language models without expensive post-training. It combines an advanced implementation of directional ablation, also known as "abliteration"...

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...

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...

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...

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...

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 :...

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...

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...

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...

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...

CVE-2026-93135

A flaw was found in the Linux kernel's Berkeley Packet Filter BPF. When the Just-In-Time JIT compiler is unavailable or fails, BPF programs that use inlined helper functions are processed by the interpreter with unpatched helper identifiers. This incorrect processing can lead to an instruction...

CVE-2026-98838

In the Linux kernel, the following vulnerability has been resolved: vt: skip screen update for DEC alignment test on backgroup consoles BUG Recently, we encountered a KASAN warning as follows: BUG: KASAN: slab-out-of-bounds in fbpadalignedbuffer+0x11f/0x140 Read of size 1 at addr ff1100015fd9f6a4...

Linux Kernel Security Vulnerabilities

The Linux kernel version 2.6.12 has a security vulnerability. This vulnerability arises from the virtual console failing to execute the conshouldupdate check when processing the ESC 8 path during DEC alignment tests. As a result, after changing the font size in the invisible virtual console, the...

CVE-2026-110596

A flaw was found in quirc. This vulnerability allows an attacker to cause a Denial of Service DoS by providing a specially crafted QR code image. When processing manipulated patterns within the image, the library enters an excessive loop during alignment calculations. This behavior exhausts syste...

Astra Linux – Vulnerability in freerdp3

FreeRDP is a free implementation of the Remote Desktop Protocol. Prior to version 3.24.0, division by zero occurred in MS-ADPCM and IMA-ADPCM decoders when nBlockAlign was 0, resulting in a crash. In libfreerdp/codec/dsp.c, both ADPCM decoders use size % blocksize, where blocksize =...

Astra Linux – Vulnerability in Linux 6.1

In the Linux kernel, the following vulnerabilities have been resolved: ARM: 9475/1: Use of a byte load operation for accessing the KASAN VMAP stack shadow. The commit 44e9a3bb76e5 “ARM: 9430/1: Entry: Perform a dummy read from the KASAN VMAP stack shadow” adds a dummy read from the KASAN VMAP sta...

Astra Linux – Vulnerability found in Linux 5.10, Linux 6.1, and Linux 5.15

In the Linux kernel, the following vulnerabilities have been resolved: i40e: added validation for the ringlen parameter. The ringlen parameter provided by the virtual function VF is assigned directly to the hardware memory context HMC without any validation. To address this issue, a upper boundar...

Astra Linux – Vulnerability found in Linux 5.15, Linux 6.1

In the Linux kernel, the following vulnerability has been resolved: bus: mhi: host – Added an alignment check for the event ring read pointer. Although we check the event ring read pointer using “isvalidringptr” to ensure it is within the buffer range, there is another risk that the pointer might...

Astra Linux – Vulnerability in Linux 5.15

In the Linux kernel, the following vulnerability has been resolved: media: imx-jpeg: Buffer size aligned upwards. The hardware can support any image size WxH, with arbitrary W image width and H image height dimensions. The buffer size is aligned upwards for both the encoder and the decoder, while...

Astra Linux – Vulnerability in Linux 6.1

In the Linux kernel, the following vulnerabilities have been resolved: arm64: Do not call NULL in docompatalignmentfixup. doalignmentt32tohandler only fixes alignment faults for specific instructions; otherwise, it returns NULL e.g., for LDREX. When this occurs, a signal is sent to the caller...