From Split to Share: Private Inference with Distributed Feature Sharing

Cloud-based Machine Learning as a Service MLaaS raises serious privacy concerns when handling sensitive client data. Existing Private Inference PI methods face a fundamental trade-off between privacy and efficiency: cryptographic approaches offer strong protection but incur high computational...

Backdoors & Breaches: How Talos is helping humanitarian aid NGOs prepare for cyber attacks

In 2023, Talos collaborated with NetHope and Cisco Crisis Response to create a customized Backdoors & Breaches expansion deck for international humanitarian organizations, addressing their unique cybersecurity challenges. The new expansion deck helps NGOs with constrained budgets improve proactiv...

A Survey on Data Security in Large Language Models

Large Language Models LLMs, now a foundation in advancing natural language processing, power applications such as text generation, machine translation, and conversational systems. Despite their transformative potential, these models inherently rely on massive amounts of training data, often...

DINA: a Dual Defense Framework against Internal Noise and External Attacks in Natural Language Processing

As large language models LLMs and generative AI become increasingly integrated into customer service and moderation applications, adversarial threats emerge from both external manipulations and internal label corruption. In this work, we identify and systematically address these dual adversarial...

CVE-2025-50472

The modelscope/ms-swift library thru 2.6.1 is vulnerable to arbitrary code execution through deserialization of untrusted data within the loadmodelmeta function of the ModelFileSystemCache class. Attackers can execute arbitrary code and commands by crafting a malicious serialized .mdl payload,...

PT-2025-43576

Name of the Vulnerable Software and Affected Versions ms-swift affected versions not specified Description Command injection is possible through the LLM Training interface of the web-ui. An attacker can manipulate the --output dir parameter to execute arbitrary commands on the host system. This...

Exploit for Incorrect Default Permissions in Microsoft

This List is no longer updated. Awesome Red Teaming List of Awesome Red Team / Red Teaming Resources This list is for anyone wishing to learn about Red Teaming but do not have a starting point. Anyway, this is a living resources and will update regularly with latest Adversarial Tactics and...

EdgeAgentX-DT: Integrating Digital Twins and Generative AI for Resilient Edge Intelligence in Tactical Networks

We introduce EdgeAgentX-DT, an advanced extension of the EdgeAgentX framework that integrates digital twin simulations and generative AI-driven scenario training to significantly enhance edge intelligence in military networks. EdgeAgentX-DT utilizes network digital twins, virtual replicas...

Enhancing IoT Intrusion Detection Systems through Adversarial Training

The augmentation of Internet of Things IoT devices transformed both automation and connectivity but revealed major security vulnerabilities in networks. We address these challenges by designing a robust intrusion detection system IDS to detect complex attacks by learning patterns from the...

Enabling Cyber Security Education through Digital Twins and Generative AI

Digital Twins DTs are gaining prominence in cybersecurity for their ability to replicate complex IT Information Technology, OT Operational Technology, and IoT Internet of Things infrastructures, allowing for real time monitoring, threat analysis, and system simulation. This study investigates how...

Learning-Based Privacy-Preserving Graph Publishing against Sensitive Link Inference Attacks

Publishing graph data is widely desired to enable a variety of structural analyses and downstream tasks. However, it also potentially poses severe privacy leakage, as attackers may leverage the released graph data to launch attacks and precisely infer private information such as the existence of...

WeTransfer walks back clause that said it would train AI on your files

File sharing site WeTransfer has rolled back language that allowed it to train machine learning models on any files that its users uploaded. The change was made after criticisms from its users. The company had quietly inserted the new language in the terms and conditions on its website. Sometime...

microcode_ctl: From CVEorg collector

New Spectre-v2 attack classes have been discovered within CPU architectures that enable self-training exploitation of speculative execution within the same privilege domain. These novel techniques bypass existing hardware and software mitigations, including IBPB, eIBRS, and BHINO, by leveraging...

PRM-Free Security Alignment of Large Models Via Red Teaming and Adversarial Training

Large Language Models LLMs have demonstrated remarkable capabilities across diverse applications, yet they pose significant security risks that threaten their safe deployment in critical domains. Current security alignment methodologies predominantly rely on Process Reward Models PRMs to evaluate...

PLA: Prompt Learning Attack against Text-To-Image Generative Models

Text-to-Image T2I models have gained widespread adoption across various applications. Despite the success, the potential misuse of T2I models poses significant risks of generating Not-Safe-For-Work NSFW content. To investigate the vulnerability of T2I models, this paper delves into adversarial...

Split Happens: Combating Advanced Threats with Split Learning and Function Secret Sharing

Split Learning SL -- splits a model into two distinct parts to help protect client data while enhancing Machine Learning ML processes. Though promising, SL has proven vulnerable to different attacks, thus raising concerns about how effective it may be in terms of data privacy. Recent works have...

Exploit for CVE-2025-49113

Roundcube RCE Lab CVE-2025-49113 !Open in GitHub Codespac...

Exploit for CVE-2025-49113

Roundcube RCE Lab CVE-2025-49113 !Open in GitHub Codespac...

When and Where Do Data Poisons Attack Textual Inversion?

Poisoning attacks pose significant challenges to the robustness of diffusion models DMs. In this paper, we systematically analyze when and where poisoning attacks textual inversion TI, a widely used personalization technique for DMs. We first introduce Semantic Sensitivity Maps, a novel method fo...

Entangled Threats: a Unified Kill Chain Model for Quantum Machine Learning Security

Quantum Machine Learning QML systems inherit vulnerabilities from classical machine learning while introducing new attack surfaces rooted in the physical and algorithmic layers of quantum computing. Despite a growing body of research on individual attack vectors - ranging from adversarial poisoni...