A study compared the vulnerability of C programs generated by nine state-of-the-art Large Language Models (LLMs) using a zero-shot prompt. The researchers introduced FormAI-v2, a dataset of 331,000 C programs generated by these LLMs, and found that at least 62.07% of the generated programs contained vulnerabilities, detected via formal verification. The research highlights the need for risk assessment and validation when deploying LLM-generated code in production environments.
The paper introduces VENOM, a text-driven framework for generating high-quality unrestricted adversarial examples using diffusion models. VENOM unifies image content generation and adversarial synthesis into a single reverse diffusion process, enhancing both attack success rate and image quality. The framework incorporates an adaptive adversarial guidance strategy with momentum to ensure the generated adversarial examples align with the distribution of natural images.
The paper introduces ScoreAdv, a novel approach for generating natural adversarial examples (UAEs) using diffusion models. It incorporates an adversarial guidance mechanism and saliency maps to shift the sampling distribution and inject visual information. Experiments on ImageNet and CelebA datasets demonstrate state-of-the-art attack success rates, image quality, and robustness against defenses.
KPMG's report, "Breaking point or breakthrough: the borderless adversary," examines the evolving landscape of AI and its profound impact on cyber security. The report highlights that AI is increasingly used by threat actors, creating a "borderless adversary" that transcends traditional defense perimeters. It stresses the urgent need for organizations to understand these AI-driven attack vectors and to adapt their cyber security strategies to both mitigate risks and leverage AI for enhanced defense. Why it matters: This report provides critical insights for organizations in the Middle East and globally, urging them to proactively integrate AI into their cyber security frameworks to protect against sophisticated threats in the digital age.