Scam Shield: Multi-Model Voting and Fine-Tuned LLMs against Adversarial Attacks

Scam detection remains a critical challenge in cybersecurity as adversaries craft messages that evade automated filters. We propose a Hierarchical Scam Detection System HSDS that combines a lightweight multi-model voting front end with a fine-tuned LLaMA 3.1 8B Instruct back end to improve accura...

ABC Fine Wine & Spirits Android App 安全漏洞

ABC Fine Wine & Spirits Android App is a wine shopping app by ABC Fine Wine & Spirits. A security vulnerability exists in ABC Fine Wine & Spirits Android App v.11.27.5 and earlier versions, which stems from improper access control of the login mechanism and could lead to bypassing login checks an...

CVE-2025-61115

CVE-2025-61115 affects ABC Fine Wine & Spirits Android App versions v.11.27.5 and earlier (package com.cta.abcfinewineandspirits). The root cause is improper access control in the login mechanism: the app does not properly validate user passwords during authentication, allowing bypass of login ch...

Jailbreak Mimicry: Automated Discovery of Narrative-Based Jailbreaks for Large Language Models

Large language models LLMs remain vulnerable to sophisticated prompt engineering attacks that exploit contextual framing to bypass safety mechanisms, posing significant risks in cybersecurity applications. We introduce Jailbreak Mimicry, a systematic methodology for training compact attacker mode...

REx86: A Local Large Language Model for Assisting in X86 Assembly Reverse Engineering

Reverse engineering RE of x86 binaries is indispensable for malware and firmware analysis, but remains slow due to stripped metadata and adversarial obfuscation. Large Language Models LLMs offer potential for improving RE efficiency through automated comprehension and commenting, but cloud-hosted...

Bloodroot: When Watermarking Turns Poisonous for Stealthy Backdoor

Backdoor data poisoning is a crucial technique for ownership protection and defending against malicious attacks. Embedding hidden triggers in training data can manipulate model outputs, enabling provenance verification, and deterring unauthorized use. However, current audio backdoor methods are...

EUVD-2005-1498

Malware in sbrugna...

EUVD-2020-3634

Malware in sbrugna...

EUVD-2008-1816

Malware in sbrugna...

P2P: A Poison-To-Poison Remedy for Reliable Backdoor Defense in LLMs

During fine-tuning, large language models LLMs are increasingly vulnerable to data-poisoning backdoor attacks, which compromise their reliability and trustworthiness. However, existing defense strategies suffer from limited generalization: they only work on specific attack types or task settings...

EUVD-2024-2914

Malicious code in bioql PyPI...

EUVD-2024-19186

Malicious code in bioql PyPI...

EUVD-2023-47945

Malicious code in bioql PyPI...

EUVD-2024-2822

Malicious code in bioql PyPI...

EUVD-2024-20867

Malicious code in bioql PyPI...

EUVD-2021-7351

Malicious code in bioql PyPI...

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...

Beyond Surface Alignment: Rebuilding LLMs Safety Mechanism Via Probabilistically Ablating Refusal Direction

Jailbreak attacks pose persistent threats to large language models LLMs. Current safety alignment methods have attempted to address these issues, but they experience two significant limitations: insufficient safety alignment depth and unrobust internal defense mechanisms. These limitations make...

Beyond Classification: Evaluating LLMs for Fine-Grained Automatic Malware Behavior Auditing

Automated malware classification has achieved strong detection performance. Yet, malware behavior auditing seeks causal and verifiable explanations of malicious activities -- essential not only to reveal what malware does but also to substantiate such claims with evidence. This task is challengin...

XOffense: an AI-Driven Autonomous Penetration Testing Framework with Offensive Knowledge-Enhanced LLMs and Multi Agent Systems

This work introduces xOffense, an AI-driven, multi-agent penetration testing framework that shifts the process from labor-intensive, expert-driven manual efforts to fully automated, machine-executable workflows capable of scaling seamlessly with computational infrastructure. At its core, xOffense...