AI Sec Watch

Researchers propose a generative model for time series (sequences of data points over time) based on Schrödinger bridge, a mathematical technique that uses optimal transport (finding the most efficient way to transform one data distribution into another) to create synthetic time series data. The model estimates unknown functions from real data using nonparametric methods (techniques that don't assume a specific underlying mathematical form) and generates new synthetic samples that preserve the temporal patterns in the original data.

A missing authorization vulnerability (CWE-862, a weakness where the system fails to check if a user has permission to access something) was found in the Recorp AI Content Writing Assistant plugin for WordPress, affecting versions up to 1.1.7. This flaw allows attackers to exploit incorrectly configured access control, meaning they could potentially access features or data they shouldn't be able to reach.

This research studied what makes knowledge workers (people whose jobs involve handling information) want to use ChatGPT at work, using technology affordance and constraints theory (a framework explaining how tools enable certain actions while limiting others). The study found that ChatGPT's benefits like automation, information quality, and productivity boost adoption, but concerns about risk and lack of regulation reduce it. Personal innovativeness (how open someone is to new ideas) and supportive workplace culture help workers embrace ChatGPT despite their concerns.

CVE-2025-62116 is a missing authorization vulnerability (a security flaw where the software fails to check if a user has permission to perform an action) in Quadlayers AI Copilot that affects versions up to 1.4.7. The vulnerability allows attackers to exploit incorrectly configured access control security levels, meaning they may be able to access or perform actions they shouldn't be allowed to.

This presentation covers security vulnerabilities found in agentic systems, which are AI agents (systems that can take actions autonomously) that can use computers and write code. The talk includes demonstrations of exploits discovered during the Month of AI Bugs, a security research initiative focused on finding bugs in AI systems.

This is a release of llama-index v0.14.12, a framework for building AI applications, containing various updates across multiple components including bug fixes, new features for asynchronous tool support, and improvements to integrations with services like OpenAI, Google, Anthropic, and various vector stores (databases that store numerical representations of data for AI searching). Key fixes address issues like crashes in logging, missing parameters in tool handling, and compatibility improvements for newer Python versions.

This research explores multiresolution learning, a training method where AI models learn from data at multiple levels of detail, starting from very coarse versions and progressively moving to finer ones. The study shows this approach makes deep neural networks (DNNs, which are AI systems with many layers) more robust against noise and adversarial attacks (deliberate attempts to fool the AI) while maintaining accuracy, without requiring extra computing power compared to traditional training methods.

LMDeploy is a toolkit for compressing, deploying, and serving large language models (LLMs). Prior to version 0.11.1, the software had an insecure deserialization vulnerability (unsafe conversion of data back into executable code) where it used torch.load() without the weights_only=True parameter when opening model checkpoint files, allowing attackers to run arbitrary code on a victim's machine by tricking them into loading a malicious .bin or .pt model file.

Hypergraph Neural Networks (HGNNs, which are AI models that learn from data where connections can link multiple items together instead of just pairs) can be weakened by structural attacks that corrupt their connections and reduce accuracy. HGNN Shield is a defense framework with two main components: Hyperedge-Dependent Estimation (which assesses how important each connection is within the network) and High-Order Shield (which detects and removes harmful connections before the AI processes data). Experiments show the framework improves performance by an average of 9.33% compared to existing defenses.