Tootfinder

SDD: Self-Degraded Defense against Malicious Fine-tuning
Zixuan Chen, Weikai Lu, Xin Lin, Ziqian Zeng
https://arxiv.org/abs/2507.21182 https://arxiv.org/pd…

SDD: Self-Degraded Defense against Malicious Fine-tuning
Open-source Large Language Models (LLMs) often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To counter this, we theoretically uncover why malicious fine-tuning succeeds and identify potential defense strategies. Building on the theoretical analysis, we introduce the Self-Degraded Defense (SDD) framework. SDD encourages LLMs to produce high-quality but irr…

Please Note: If you receive a reply that looks like this, it is fake and a malicious scam. Do not click on the links in the post. Report the post for spam to the Pawb moderation team and we will handle it.
Mastodon will never ask for your identification on our servers (or in general). On Pawb servers, we control the operations and we also will not ask for identification in this manner either. If that was required for some reason, we would contact the user directly and …

Look, Jeff Atwood, it is difficult to take you seriously when you write authoritatively on a subject you clearly don’t understand.
GDPR doesn’t mandate cookie notices.
Cookie notices are *malicious compliance* by the surveillance-driven adtech industry.
If you’re not tracking people, you do not need a cookie notice, period.
If you’re only using first-party cookies for functional reasons, you do not need a cookie notice, period.
If you’re using third-party co…

"We simply don’t know to defend against these attacks. We have zero agentic AI systems that are secure against these attacks.[…] It’s an existential problem that, near as I can tell, most people developing these technologies are just pretending isn’t there."
https://www.

MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?
Muntasir Wahed, Xiaona Zhou, Kiet A. Nguyen, Tianjiao Yu, Nirav Diwan, Gang Wang, Dilek Hakkani-T\"ur, Ismini Lourentzou
https://arxiv.org/abs/2507.19598

MOCHA: Are Code Language Models Robust Against Multi-Turn Malicious Coding Prompts?
Recent advancements in Large Language Models (LLMs) have significantly enhanced their code generation capabilities. However, their robustness against adversarial misuse, particularly through multi-turn malicious coding prompts, remains underexplored. In this work, we introduce code decomposition attacks, where a malicious coding task is broken down into a series of seemingly benign subtasks across multiple conversational turns to evade safety filters. To facilitate systematic evaluation, we int…

packet_delays: Internet packet delays (2002)
A network representing the difference in delay observed by packet probes sent from a computer at Rice University to similar machines at different universities, in c.2002. The edge weight denotes the difference in delay of the packet in milliseconds.
This network has 10 nodes and 9567 edges.
Tags: Technological, Communication, Weighted

Breaking down ‘EchoLeak’, the First Zero-Click AI Vulnerability Enabling Data Exfiltration from Microsoft 365 Copilot.
Aim Labs reported CVE-2025-32711 against Microsoft 365 Copilot back in January, and the fix is now rolled out.
This is an extended variant of the prompt injection exfiltration attacks we've seen in a dozen different products already:
an attacker gets malicious instructions into an LLM system which cause it to access private data and then embed that in …

Nahe dem #Gletscher #Múlajökull in #Island zeigt sich im Sommer eine farbenreiche Landschaft.
Sedimentreiches

Este es un buen artículo de opinión para entender cómo la administración de Rodrigo Chaves Robles (alias zoodrigo, el presidente de Costa Rica acosador sexual que llegó al poder violando leyes de financiamiento de campañas políticas y parece gobernar para no estorbar al narco) ha hecho un daño enorme a instituciones públicas "desde adentro": poniendo a jerarcas "sumisos y servirles" en puestos de juntas directivas de instituciones autónomas para que tomen decisiones contr…

Breaking Obfuscation: Cluster-Aware Graph with LLM-Aided Recovery for Malicious JavaScript Detection
Zhihong Liang, Xin Wang, Zhenhuang Hu, Liangliang Song, Lin Chen, Jingjing Guo, Yanbin Wang, Ye Tian
https://arxiv.org/abs/2507.22447

Breaking Obfuscation: Cluster-Aware Graph with LLM-Aided Recovery for Malicious JavaScript Detection
With the rapid expansion of web-based applications and cloud services, malicious JavaScript code continues to pose significant threats to user privacy, system integrity, and enterprise security. But, detecting such threats remains challenging due to sophisticated code obfuscation techniques and JavaScript's inherent language characteristics, particularly its nested closure structures and syntactic flexibility. In this work, we propose DeCoda, a hybrid defense framework that combines large langu…