RAG Security and Privacy: Formalizing the Threat Model and Attack Surface

Retrieval-Augmented Generation RAG is an emerging approach in natural language processing that combines large language models LLMs with external document retrieval to produce more accurate and grounded responses. While RAG has shown strong potential in reducing hallucinations and improving factua...

A Survey and Evaluation Framework for Secure DNS Resolution

Since security was not among the original design goals of the Domain Name System herein called Vanilla DNS, many secure DNS schemes have been proposed to enhance the security and privacy of the DNS resolution process. Some proposed schemes aim to replace the existing DNS infrastructure entirely,...

Adversarial Bug Reports As a Security Risk in Language Model-Based Automated Program Repair

Large Language Model LLM - based Automated Program Repair APR systems are increasingly integrated into modern software development workflows, offering automated patches in response to natural language bug reports. However, this reliance on untrusted user input introduces a novel and underexplored...

CVE-2025-9190

The configuration of Cursor on macOS, specifically the "RunAsNode" fuse enabled, allows a local attacker with unprivileged access to execute arbitrary code that inherits Cursor TCC Transparency, Consent, and Control permissions. Acquired resource access is limited to previously granted permission...

CVE-2025-9190 TCC Bypass via misconfigured Node fuses in Cursor

The configuration of Cursor on macOS, specifically the "RunAsNode" fuse enabled, allows a local attacker with unprivileged access to execute arbitrary code that inherits Cursor TCC Transparency, Consent, and Control permissions. Acquired resource access is limited to previously granted permission...

Cyber Risks to Next-Gen Brain-Computer Interfaces: Analysis and Recommendations

Brain-computer interfaces BCIs show enormous potential for advancing personalized medicine. However, BCIs also introduce new avenues for cyber-attacks or security compromises. In this article, we analyze the problem and make recommendations for device manufacturers to better secure devices and to...

Physical Attacks Leading to Bypass of ASP Boot ROM Secure Boot

Summary Researchers shared a report titled “Code Execution on Zen 4 PSP using Voltage Fault Injection.” In the paper, the researchers reported their findings on Voltage Fault Injection VFI attacks targeting AMD “Zen 4” CPUs, specifically the Ryzen™ 8600G model. The researchers claim these types o...

Narrowing the Gap between TEEs Threat Model and Deployment Strategies

Confidential Virtual Machines CVMs provide isolation guarantees for data in use, but their threat model does not include physical level protection and side-channel attacks. Therefore, current deployments rely on trusted cloud providers to host the CVMs' underlying infrastructure. However, TEE...

Practical Adversarial Attacks on Stochastic Bandits Via Fake Data Injection

Adversarial attacks on stochastic bandits have traditionally relied on some unrealistic assumptions, such as per-round reward manipulation and unbounded perturbations, limiting their relevance to real-world systems. We propose a more practical threat model, Fake Data Injection, which reflects...

Breaking the Gold Standard: Extracting Forgotten Data under Exact Unlearning in Large Language Models

Large language models are typically trained on datasets collected from the web, which may inadvertently contain harmful or sensitive personal information. To address growing privacy concerns, unlearning methods have been proposed to remove the influence of specific data from trained models. Of...

CVE-2024-35238

Minder by Stacklok is an open source software supply chain security platform. Minder prior to version 0.0.51 is vulnerable to a denial-of-service DoS attack which could allow an attacker to crash the Minder server and deny other users access to it. The root cause of the vulnerability is that...

CVE-2024-31837

DMitry Deepmagic Information Gathering Tool 1.3a has a format-string vulnerability, with a threat model similar to CVE-2017-7938...

The Hidden Dangers of Browsing AI Agents

Autonomous browsing agents powered by large language models LLMs are increasingly used to automate web-based tasks. However, their reliance on dynamic content, tool execution, and user-provided data exposes them to a broad attack surface. This paper presents a comprehensive security evaluation of...

Efficient Full-Stack Private Federated Deep Learning with Post-Quantum Security

Federated learning FL enables collaborative model training while preserving user data privacy by keeping data local. Despite these advantages, FL remains vulnerable to privacy attacks on user updates and model parameters during training and deployment. Secure aggregation protocols have been...

Securing Agentic AI: a Comprehensive Threat Model and Mitigation Framework for Generative AI Agents

As generative AI GenAI agents become more common in enterprise settings, they introduce security challenges that differ significantly from those posed by traditional systems. These agents are not just LLMs; they reason, remember, and act, often with minimal human oversight. This paper introduces ...

Enhancing Leakage Attacks on Searchable Symmetric Encryption Using LLM-Based Synthetic Data Generation

Searchable Symmetric Encryption SSE enables efficient search capabilities over encrypted data, allowing users to maintain privacy while utilizing cloud storage. However, SSE schemes are vulnerable to leakage attacks that exploit access patterns, search frequency, and volume information. Existing...

CVE-2024-53983

The Backstage Scaffolder plugin Houses types and utilities for building scaffolder-related modules. A vulnerability is identified in Backstage Scaffolder template functionality where Server-Side Template Injection SSTI can be exploited to perform Git config injection. The vulnerability allows an...

CVE-2024-53983 Server-side request forgery in Backstage Scaffolder plugin

The Backstage Scaffolder plugin Houses types and utilities for building scaffolder-related modules. A vulnerability is identified in Backstage Scaffolder template functionality where Server-Side Template Injection SSTI can be exploited to perform Git config injection. The vulnerability allows an...

CVE-2024-39249

Async = 2.6.4 and = 3.2.5 are vulnerable to ReDoS Regular Expression Denial of Service while parsing function in autoinject function. NOTE: this is disputed by the supplier because there is no realistic threat model: regular expressions are not used with untrusted input...

UBUNTU-CVE-2024-39249

Async = 2.6.4 and = 3.2.5 are vulnerable to ReDoS Regular Expression Denial of Service while parsing function in autoinject function. NOTE: this is disputed by the supplier because there is no realistic threat model: regular expressions are not used with untrusted input...