Enhancing Targeted Adversarial Attacks on Large Vision-Language Models through Intermediate Projector Guidance

Targeted adversarial attacks are essential for proactively identifying security flaws in Vision-Language Models before real-world deployment. However, current methods perturb images to maximize global similarity with the target text or reference image at the encoder level, collapsing rich visual...

Consiglieres in the Shadow: Understanding the Use of Uncensored Large Language Models in Cybercrimes

The advancement of AI technologies, particularly Large Language Models LLMs, has transformed computing while introducing new security and privacy risks. Prior research shows that cybercriminals are increasingly leveraging uncensored LLMs ULLMs as backends for malicious services. Understanding the...

Mitigating Jailbreaks with Intent-Aware LLMs

Despite extensive safety-tuning, large language models LLMs remain vulnerable to jailbreak attacks via adversarially crafted instructions, reflecting a persistent trade-off between safety and task performance. In this work, we propose Intent-FT, a simple and lightweight fine-tuning approach that...

BERTector: Intrusion Detection Based on Joint-Dataset Learning

Intrusion detection systems IDS are facing challenges in generalization and robustness due to the heterogeneity of network traffic and the diversity of attack patterns. To address this issue, we propose a new joint-dataset training paradigm for IDS and propose a scalable BERTector framework based...

Code Vulnerability Detection across Different Programming Languages with AI Models

Security vulnerabilities present in a code that has been written in diverse programming languages are among the most critical yet complicated aspects of source code to detect. Static analysis tools based on rule-based patterns usually do not work well at detecting the context-dependent bugs and...

A Real-Time, Self-Tuning Moderator Framework for Adversarial Prompt Detection

Ensuring LLM alignment is critical to information security as AI models become increasingly widespread and integrated in society. Unfortunately, many defenses against adversarial attacks and jailbreaking on LLMs cannot adapt quickly to new attacks, degrade model responses to benign prompts, or...

PT-2025-32492 · Pypi · Ms-Swift

I. Detailed Description: 1. Install ms-swift pip install ms-swift -U 2. Start web-ui swift web-ui --lang en 3. After startup, access through browser at http://localhost:7860/ to see the launched fine-tuning framework program 4. Fill in necessary parameters In the LLM Training interface, fill in...

org.keycloak/keycloak-services: Privilege Escalation in Keycloak Admin Console (FGAPv2 Enabled)

A flaw was found in the Keycloak identity and access management system when Fine-Grained Admin PermissionsFGAPv2 are enabled. An administrative user with the manage-users role can escalate their privileges to realm-admin due to improper privilege enforcement. This vulnerability allows unauthorize...

SDD: Self-Degraded Defense against Malicious Fine-Tuning

Open-source Large Language Models LLMs often employ safety alignment methods to resist harmful instructions. However, recent research shows that maliciously fine-tuning these LLMs on harmful data can easily bypass these safeguards. To counter this, we theoretically uncover why malicious fine-tuni...

Privilege Escalation

org.keycloak, keycloak-services is vulnerable to privilege escalation. The vulnerability is due to improper privilege enforcement when Fine-Grained Admin Permissions FGAPv2 are enabled, which allows an attacker with the manage-users role to escalate privileges to realm-admin...

LoRA-Leak: Membership Inference Attacks against LoRA Fine-Tuned Language Models

Language Models LMs typically adhere to a "pre-training and fine-tuning" paradigm, where a universal pre-trained model can be fine-tuned to cater to various specialized domains. Low-Rank Adaptation LoRA has gained the most widespread use in LM fine-tuning due to its lightweight computational cost...

Scaling Decentralized Learning with FLock

Fine-tuning the large language models LLMs are prevented by the deficiency of centralized control and the massive computing and communication overhead on the decentralized schemes. While the typical standard federated learning FL supports data privacy, the central server requirement creates a...

Duplicate Advisory: Keycloak Privilege Escalation Vulnerability in Admin Console (FGAPv2 Enabled)

Duplicate Advisory This advisory has been withdrawn because it is a duplicate of GHSA-27gp-8389-hm4w. This link is maintained to preserve external references. Original Description A flaw was found in the Keycloak identity and access management system when Fine-Grained Admin Permissions FGAPv2 are...

CVE-2025-7784 Org.keycloak/keycloak-services: privilege escalation in keycloak admin console (fgapv2 enabled)

A flaw was found in the Keycloak identity and access management system when Fine-Grained Admin PermissionsFGAPv2 are enabled. An administrative user with the manage-users role can escalate their privileges to realm-admin due to improper privilege enforcement. This vulnerability allows unauthorize...

CVE-2025-7784 Org.keycloak/keycloak-services: privilege escalation in keycloak admin console (fgapv2 enabled)

A flaw was found in the Keycloak identity and access management system when Fine-Grained Admin PermissionsFGAPv2 are enabled. An administrative user with the manage-users role can escalate their privileges to realm-admin due to improper privilege enforcement. This vulnerability allows unauthorize...

CVE-2025-7784 Org.keycloak/keycloak-services: privilege escalation in keycloak admin console (fgapv2 enabled)

A flaw was found in the Keycloak identity and access management system when Fine-Grained Admin PermissionsFGAPv2 are enabled. An administrative user with the manage-users role can escalate their privileges to realm-admin due to improper privilege enforcement. This vulnerability allows unauthorize...

CVE-2025-7784

CVE-2025-7784 - Keycloak FGAPv2 Privilege Escalation This entry describes a privilege-escalation vulnerability in Keycloak when Fine-Grained Admin Permissions (FGAPv2) are enabled. An administrative user who holds the manage-users role can elevate themselves to realm-admin due to improper privile...

CVE-2025-7784: Improper Privilege Management

A flaw was found in the Keycloak identity and access management system when Fine-Grained Admin PermissionsFGAPv2 are enabled. An administrative user with the manage-users role can escalate their privileges to realm-admin due to improper privilege enforcement. This vulnerability allows unauthorize...

Jailbreak-Tuning: Models Efficiently Learn Jailbreak Susceptibility

AI systems are rapidly advancing in capability, and frontier model developers broadly acknowledge the need for safeguards against serious misuse. However, this paper demonstrates that fine-tuning, whether via open weights or closed fine-tuning APIs, can produce helpful-only models. In contrast to...

Accelerating Automatic Program Repair with Dual Retrieval-Augmented Fine-Tuning and Patch Generation on Large Language Models

Automated Program Repair APR is essential for ensuring software reliability and quality while enhancing efficiency and reducing developers' workload. Although rule-based and learning-based APR methods have demonstrated their effectiveness, their performance was constrained by the defect type of...