BreakFun: Jailbreaking LLMs Via Schema Exploitation

The proficiency of Large Language Models LLMs in processing structured data and adhering to syntactic rules is a capability that drives their widespread adoption but also makes them paradoxically vulnerable. In this paper, we investigate this vulnerability through BreakFun, a jailbreak methodolog...

SASER: Stego Attacks on Open-Source LLMs

Open-source large language models LLMs have demonstrated considerable dominance over proprietary LLMs in resolving neural processing tasks, thanks to the collaborative and sharing nature. Although full access to source codes, model parameters, and training data lays the groundwork for transparenc...

iommu/s390: Make attach succeed when the device was surprise removed

...

EUVD-2017-8797

Malware in sbrugna...

EUVD-2007-0008

Malware in sbrugna...

EUVD-2025-29147

Malicious code in bioql PyPI...

EUVD-2025-24016

Malicious code in bioql PyPI...

EUVD-2025-22670

Malicious code in bioql PyPI...

EUVD-2022-55529

Malicious code in bioql PyPI...

EUVD-2025-31985

Malicious code in bioql PyPI...

EUVD-2025-26464

Malicious code in bioql PyPI...

EUVD-2021-31872

Malicious code in bioql PyPI...

CVE-2022-50433

In the Linux kernel, the following vulnerability has been resolved: efi: ssdt: Don't free memory if ACPI table was loaded successfully Amadeusz reports KASAN use-after-free errors introduced by commit 3881ee0b1edc "efi: avoid efivars layer when loading SSDTs from variables". The problem appears t...

Backdoor Attacks against Speech Language Models

Large Language Models LLMs and their multimodal extensions are becoming increasingly popular. One common approach to enable multimodality is to cascade domain-specific encoders with an LLM, making the resulting model inherit vulnerabilities from all of its components. In this work, we present the...

Breaking the Code: Security Assessment of AI Code Agents through Systematic Jailbreaking Attacks

Code-capable large language model LLM agents are increasingly embedded into software engineering workflows where they can read, write, and execute code, raising the stakes of safety-bypass "jailbreak" attacks beyond text-only settings. Prior evaluations emphasize refusal or harmful-text detection...

kernel: drm/vkms: Fix use after free and double free on init error

In the Linux kernel, the following vulnerability has been resolved: drm/vkms: Fix use after free and double free on init error If the driver initialization fails, the vkmsexit function might access an uninitialized or freed defaultconfig pointer and it might double free it. Fix both possible erro...

Vision Transformers: the Threat of Realistic Adversarial Patches

The increasing reliance on machine learning systems has made their security a critical concern. Evasion attacks enable adversaries to manipulate the decision-making processes of AI systems, potentially causing security breaches or misclassification of targets. Vision Transformers ViTs have gained...

DEBIAN-CVE-2025-39847

In the Linux kernel, the following vulnerability has been resolved: ppp: fix memory leak in padcompressskb If allocskb fails in padcompressskb, it returns NULL without releasing the old skb. The caller does: skb = padcompressskbppp, skb; if !skb goto drop; drop: kfreeskbskb; When padcompressskb...

SUSE CVE-2023-53295

In the Linux kernel, the following vulnerability has been resolved: udf: Do not update file length for failed writes to inline files When write to inline file fails or happens only partly, we still updated length of inline data as if the whole write succeeded. Fix the update of length of inline...

DEBIAN-CVE-2023-53295

In the Linux kernel, the following vulnerability has been resolved: udf: Do not update file length for failed writes to inline files When write to inline file fails or happens only partly, we still updated length of inline data as if the whole write succeeded. Fix the update of length of inline...