Uncensored-AI

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"...

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"...

ablation

Ablation is a reverse engineering framework that runs autonomously with AI coding agents. Capabilities 31 Decompilers, Lifters & ISAs Native CPUs ISA| Variants ---|--- x86| x86-32 · x86-64 ARM| ARM-32 · ARM-64 · Thumb MIPS| MIPS-32 · nanoMIPS · MIPS-64 PowerPC| PPC-32 · PPC-64 · VLE · PPC476 Book...

ablation (0.1.0), deepethogram (>=0.3.0, <=0.5.0) +7 more potentially affected by CVE-2024-5980 via pytorch-lightning (1.6.5)

pytorch-lightning PYPI version 1.6.5 is affected by a known vulnerability. The following packages have a transitive dependency on pytorch-lightning and may be impacted: - ablation 0.1.0 - deepethogram =0.3.0, =0.0.15, =1.4.0, =1.0.0, =0.1.0, =0.1.2 - run-crom 1.0.0 Source cves: CVE-2024-5980 Sour...

ablation (0.1.0), deepethogram (>=0.3.0, <=0.5.0) +7 more potentially affected by CVE-2024-5452 via pytorch-lightning (1.6.5)

pytorch-lightning PYPI version 1.6.5 is affected by a known vulnerability. The following packages have a transitive dependency on pytorch-lightning and may be impacted: - ablation 0.1.0 - deepethogram =0.3.0, =0.0.15, =1.4.0, =1.0.0, =0.1.0, =0.1.2 - run-crom 1.0.0 Source cves: CVE-2024-5452 Sour...

Circuit Discovery Helps Detect LLM Jailbreaking: A Mechanistic Interpretability Study

Despite extensive safety alignment, large language models LLMs remain vulnerable to jailbreak attacks that bypass safeguards to elicit harmful content. While prior work attributes this vulnerability to safety training limitations, the internal mechanisms by which LLMs process adversarial prompts...

Directed Symbolic Execution for Vulnerability Discovery: An LLM-Guided Approach in KLEE

Symbolic execution effectively discovers security violations but suffers from path explosion. Engines like KLEE therefore use path prioritization heuristics to order state exploration, typically optimizing code coverage. However, path prioritization can become trapped in cyclic control-flow...

Residual Observability and Attack Detectability in Encrypted OPC UA Traffic

OPC Unified Architecture OPC UA encryption conceals application-layer semantics and restricts intrusion detection to residual communication structure. Although machine learning-based intrusion detection systems IDSs can detect attacks in encrypted OPC UA traffic, the relationship between residual...

4996 (>=0.1.0, <=0.1.1), ablation (0.1.0) +30 more potentially affected by CVE-2025-3730 via torch (1.10.1)

torch PYPI version 1.10.1 is affected by a known vulnerability. The following packages have a transitive dependency on torch and may be impacted: - 4996 =0.1.0, =0.1.13, =2.0.0rc1, =0.0.1, =0.3.3, =0.1.0, =0.5.0, =0.6.0 and more Source cves: CVE-2025-3730 Source advisory: OSV:PYSEC-2026-1970...

ablation (0.1.0), deepethogram (>=0.3.0, <=0.5.0) +7 more potentially affected by CVE-2024-8019 via pytorch-lightning (1.6.5)

pytorch-lightning PYPI version 1.6.5 is affected by a known vulnerability. The following packages have a transitive dependency on pytorch-lightning and may be impacted: - ablation 0.1.0 - deepethogram =0.3.0, =0.0.15, =1.4.0, =1.0.0, =0.1.0, =0.1.2 - run-crom 1.0.0 Source cves: CVE-2024-8019 Sour...

MESA: Prioritizing Vulnerable Communication Channels for Securing Multi-Agent Systems

Multi-agent systems MAS are increasingly used to automate complex, distributed workflows. However, their inter-agent communication channels introduce new attack surfaces that remain poorly understood and are difficult to defend against. In this paper, we address how defenders should prioritize...

On the Evaluation of Spiking Neural Network Configurations for Network Intrusion Detection

Network intrusion detection is a core component of modern cybersecurity infrastructure, yet the deep learning models that dominate the field are computationally demanding, motivating interest in lightweight alternatives suited to edge and neuromorphic deployment. Spiking Neural Networks SNNs are...

Dissecting the Black Box: Circuit-Level Analysis of LLM Vulnerability Detection

Large language models LLMs can detect software vulnerabilities, but how do they actually identify vulnerable code? We address this question using mechanistic interpretability; analyzing the internal computations of a neural network to understand its reasoning process.Using Circuit Tracer on...

ablation (0.1.0), deepethogram (>=0.3.0, <=0.5.0) +7 more potentially affected by CVE-2026-31221 via pytorch-lightning (1.6.5)

pytorch-lightning PYPI version 1.6.5 is affected by a known vulnerability. The following packages have a transitive dependency on pytorch-lightning and may be impacted: - ablation 0.1.0 - deepethogram =0.3.0, =0.0.15, =1.4.0, =1.0.0, =0.1.0, =0.1.2 - run-crom 1.0.0 Source cves: CVE-2026-31221...

VulStyle: A Multi-Modal Pre-Training for Code Stylometry-Augmented Vulnerability Detection

We present VulStyle, a multi-modal software vulnerability detection model that jointly encodes function-level source code, non-terminal Abstract Syntax Tree AST structure, and code stylometry CStyle features. Prior work in code representation primarily leverages token-level models or full AST...

Towards Certified Malware Detection: Provable Guarantees against Evasion Attacks

Machine learning-based static malware detectors remain vulnerable to adversarial evasion techniques, such as metamorphic engine mutations. To address this vulnerability, we propose a certifiably robust malware detection framework based on randomized smoothing through feature ablation and targeted...

Software Vulnerability Detection Using a Lightweight Graph Neural Network

Large Language Models LLMs have emerged as a popular choice in vulnerability detection studies given their foundational capabilities, open source availability, and variety of models, but have limited scalability due to extensive compute requirements. Using the natural graph relational structure o...

4996 (>=0.1.0, <=0.1.1), ablation (0.1.0) +30 more potentially affected by CVE-2026-4538 via torch (1.10.1)

torch PYPI version 1.10.1 is affected by a known vulnerability. The following packages have a transitive dependency on torch and may be impacted: - 4996 =0.1.0, =0.1.13, =2.0.0rc1, =0.0.1, =0.3.3, =0.1.0, =0.5.0, =0.6.0 and more Source cves: CVE-2026-4538 Source advisory: OSV:PYSEC-2026-139...

Agent Privilege Separation in OpenClaw: A Structural Defense against Prompt Injection

Prompt injection remains one of the most practical attack vectors against LLM-integrated applications. We replicate the Microsoft LLMail-Inject benchmark Greshake et al., 2024 against current generation models running inside OpenClaw, an open source multitool agent platform. Our proposed defense...

PIDSMaker: Building and Evaluating Provenance-Based Intrusion Detection Systems

Recent provenance-based intrusion detection systems PIDSs have demonstrated strong potential for detecting advanced persistent threats APTs by applying machine learning to system provenance graphs. However, evaluating and comparing PIDSs remains difficult: prior work uses inconsistent preprocessi...