Security of LLM-Generated Code: A Comparative Analysis

The majority of software developers use or are planning to use Artificial Intelligence AI tools in their development processes. Their top reasons include improving productivity and faster learning. In fact, Large Language Model LLM-generated code is currently in production, including in major tec...

PT-2025-48021

An authentication bypass vulnerability has been identified in the IFTTT integration feature. A remote, authenticated attacker could leverage this vulnerability to potentially gain unauthorized access to the device. This vulnerability does not affect Wi-Fi 7 series models. Refer to the 'Security...

VEIL: Jailbreaking Text-To-Video Models Via Visual Exploitation from Implicit Language

Jailbreak attacks can circumvent model safety guardrails and reveal critical blind spots. Prior attacks on text-to-video T2V models typically add adversarial perturbations to obviously unsafe prompts, which are often easy to detect and defend. In contrast, we show that benign-looking prompts...

CompLeak: Deep Learning Model Compression Exacerbates Privacy Leakage

Model compression is crucial for minimizing memory storage and accelerating inference in deep learning DL models, including recent foundation models like large language models LLMs. Users can access different compressed model versions according to their resources and budget. However, while existi...

The vulnerability in the implementation of the GOT Mobile function in the software for graphic control panels from Mitsubishi Electric’s GOT2000 series, models GT27 and GT25, as well as the HMI platform GT SoftGOT2000, allows a perpetrator to gain unauthorized access to protected information.

The vulnerability of the GOT Mobile function implementation in Mitsubishi Electric’s GOT2000 series graphic control panels, models GT27 and GT25, as well as the HMI platform GT SoftGOT2000, involves bypassing authentication through spoofing. Exploiting this vulnerability can allow unauthorized...