Non-Adaptive Adversarial Face Generation

Adversarial attacks on face recognition systems FRSs pose serious security and privacy threats, especially when these systems are used for identity verification. In this paper, we propose a novel method for generating adversarial faces-synthetic facial images that are visually distinct yet...

User-To-PC Authentication through Confirmation on Mobile Devices: on Usability and Performance

Protecting personal computers PCs from unauthorized access typically relies on password authentication, which is know to suffer from cognitive burden and weak credentials. As many users nowadays carry mobile devices with advanced security features throughout their day, there is an opportunity to...

May I Have Your Attention? Breaking Fine-Tuning Based Prompt Injection Defenses Using Architecture-Aware Attacks

A popular class of defenses against prompt injection attacks on large language models LLMs relies on fine-tuning the model to separate instructions and data, so that the LLM does not follow instructions that might be present with data. There are several academic systems and production-level...

WordPress plugin Contact Form 7 Hide Success Message security vulnerability

WordPress and WordPress plugin are both products of the WordPress Foundation.WordPress is a blogging platform developed using the PHP language. WordPress is a blogging platform developed in the PHP language that supports personal blogs on PHP and MySQL servers.WordPress plugin is an application...

Advancing Jailbreak Strategies: a Hybrid Approach to Exploiting LLM Vulnerabilities and Bypassing Modern Defenses

The advancement of Pre-Trained Language Models PTLMs and Large Language Models LLMs has led to their widespread adoption across diverse applications. Despite their success, these models remain vulnerable to attacks that exploit their inherent weaknesses to bypass safety measures. Two primary...

Wiz Recognized as a Leader in the 2025 IDC MarketScape for CNAPP

We believe recognition in the IDC MarketScape for CNAPP reflects our commitment to innovation and customer success across cloud security...

On the Feasibility of Poisoning Text-To-Image AI Models Via Adversarial Mislabeling

Today's text-to-image generative models are trained on millions of images sourced from the Internet, each paired with a detailed caption produced by Vision-Language Models VLMs. This part of the training pipeline is critical for supplying the models with large volumes of high-quality image-captio...

InverTune: Removing Backdoors from Multimodal Contrastive Learning Models Via Trigger Inversion and Activation Tuning

Multimodal contrastive learning models like CLIP have demonstrated remarkable vision-language alignment capabilities, yet their vulnerability to backdoor attacks poses critical security risks. Attackers can implant latent triggers that persist through downstream tasks, enabling malicious control ...

Tarallo: Evading Behavioral Malware Detectors in the Problem Space

Machine learning algorithms can effectively classify malware through dynamic behavior but are susceptible to adversarial attacks. Existing attacks, however, often fail to find an effective solution in both the feature and problem spaces. This issue arises from not addressing the intrinsic...

DEBIAN-CVE-2025-37999

In the Linux kernel, the following vulnerability has been resolved: fs/erofs/fileio: call erofsonlinefoliosplit after bioaddfolio If bioaddfolio fails because it is full, erofsfileioscanfolio needs to submit the I/O request via erofsfileiorqsubmit and allocate a new I/O request with an empty stru...

CVE-2021-34370

Accela Civic Platform through 20.1 allows ssoAdapter/logoutAction.do successURL XSS. NOTE: the vendor states "there are configurable security flags and we are unable to reproduce them with the available information...

One Shot Dominance: Knowledge Poisoning Attack on Retrieval-Augmented Generation Systems

Large Language Models LLMs enhanced with Retrieval-Augmented Generation RAG have shown improved performance in generating accurate responses. However, the dependence on external knowledge bases introduces potential security vulnerabilities, particularly when these knowledge bases are publicly...

GraphQL Import Success

GraphQL schema file was successfully imported and can be used during the scan. No source data...

SafeTrans: LLM-Assisted Transpilation from C to Rust

Rust is a strong contender for a memory-safe alternative to C as a "systems" programming language, but porting the vast amount of existing C code to Rust is a daunting task. In this paper, we evaluate the potential of large language models LLMs to automate the transpilation of C code to idiomatic...

5 Tips You Should Know before Developing an Innovative Product

Are you aiming to develop an innovative startup that will make a boom effect in the modern market?…...

Distributed AI Inference: Strategies for Success

...

CVE-2022-49906 ibmvnic: Free rwi on reset success

In the Linux kernel, the following vulnerability has been resolved: ibmvnic: Free rwi on reset success Free the rwi structure in the event that the last rwi in the list processed successfully. The logic in commit 4f408e1fa6e1 "ibmvnic: retry reset if there are no other resets" introduces an issue...

CVE-2022-49906

The CVE-2022-49906 issue affects the Linux kernel ibmvnic driver: a path in the reset handling could leak 32 bytes by not freeing the rwi structure when the last rwi in the list is processed. A fix releases the rwi memory on reset success (kernel patch 4f408e1fa6e1 and related commits). Connected...

CVE-2022-49906 ibmvnic: Free rwi on reset success

In the Linux kernel, the following vulnerability has been resolved: ibmvnic: Free rwi on reset success Free the rwi structure in the event that the last rwi in the list processed successfully. The logic in commit 4f408e1fa6e1 "ibmvnic: retry reset if there are no other resets" introduces an issue...

BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-Box Large Language Models

Previous insertion-based and paraphrase-based backdoors have achieved great success in attack efficacy, but they ignore the text quality and semantic consistency between poisoned and clean texts. Although recent studies introduce LLMs to generate poisoned texts and improve the stealthiness,...