GenBreak: Red Teaming Text-To-Image Generators Using Large Language Models

Text-to-image T2I models such as Stable Diffusion have advanced rapidly and are now widely used in content creation. However, these models can be misused to generate harmful content, including nudity or violence, posing significant safety risks. While most platforms employ content moderation...

MalGEN: a Generative Agent Framework for Modeling Malicious Software in Cybersecurity

The dual use nature of Large Language Models LLMs presents a growing challenge in cybersecurity. While LLM enhances automation and reasoning for defenders, they also introduce new risks, particularly their potential to be misused for generating evasive, AI crafted malware. Despite this emerging...

GradEscape: a Gradient-Based Evader against AI-Generated Text Detectors

In this paper, we introduce GradEscape, the first gradient-based evader designed to attack AI-generated text AIGT detectors. GradEscape overcomes the undifferentiable computation problem, caused by the discrete nature of text, by introducing a novel approach to construct weighted embeddings for t...

Malicious Package

Overview coloramapkgsw is a malicious package. This package contains payloads with Windows and Linux variants that access and exfiltrate sensitive configuration information, establish remote control / remote access for the attacker, establish persistence and “command and control” C2 mechanisms...

Malicious Package

Overview Colorizator is a malicious package. This package contains payloads with Windows and Linux variants that access and exfiltrate sensitive configuration information, establish remote control / remote access for the attacker, establish persistence and “command and control” C2 mechanisms...

Fooling the Watchers: Breaking AIGC Detectors Via Semantic Prompt Attacks

The rise of text-to-image T2I models has enabled the synthesis of photorealistic human portraits, raising serious concerns about identity misuse and the robustness of AIGC detectors. In this work, we propose an automated adversarial prompt generation framework that leverages a grammar tree...

Merge Hijacking: Backdoor Attacks to Model Merging of Large Language Models

Model merging for Large Language Models LLMs directly fuses the parameters of different models finetuned on various tasks, creating a unified model for multi-domain tasks. However, due to potential vulnerabilities in models available on open-source platforms, model merging is susceptible to...

The Feasibility of Topic-Based Watermarking on Academic Peer Reviews

Large language models LLMs are increasingly integrated into academic workflows, with many conferences and journals permitting their use for tasks such as language refinement and literature summarization. However, their use in peer review remains prohibited due to concerns around confidentiality...

Adapting Novelty Towards Generating Antigens for Antivirus Systems

It is well known that anti-malware scanners depend on malware signatures to identify malware. However, even minor modifications to malware code structure results in a change in the malware signature thus enabling the variant to evade detection by scanners. Therefore, there exists the need for a...

CVE-2023-26453

Requests to cache an image could be abused to include SQL queries that would be executed unchecked. Exploiting this vulnerability requires at least access to adjacent networks of the imageconverter service, which is not exposed to public networks by default. Arbitrary SQL statements could be...

CVE-2019-13125

HaboMalHunter through 2.0.0.3 in Tencent Habo allows attackers to evade dynamic malware analysis via PIE compilation...

Fileless Remcos RAT Attack Evades Antivirus Using PowerShell Scripts

A new wave of attacks uses PowerShell and LNK files to secretly install Remcos RAT, enabling full remote…...

Learning from the Good Ones: Risk Profiling-Based Defenses against Evasion Attacks on DNNs

Safety-critical applications such as healthcare and autonomous vehicles use deep neural networks DNN to make predictions and infer decisions. DNNs are susceptible to evasion attacks, where an adversary crafts a malicious data instance to trick the DNN into making wrong decisions at inference time...

LATENT: LLM-Augmented Trojan Insertion and Evaluation Framework for Analog Netlist Topologies

Analog and mixed-signal A/MS integrated circuits ICs are integral to safety-critical applications. However, the globalization and outsourcing of A/MS ICs to untrusted third-party foundries expose them to security threats, particularly analog Trojans. Unlike digital Trojans which have been...

Towards Dataset Copyright Evasion Attack against Personalized Text-To-Image Diffusion Models

Text-to-image T2I diffusion models have rapidly advanced, enabling high-quality image generation conditioned on textual prompts. However, the growing trend of fine-tuning pre-trained models for personalization raises serious concerns about unauthorized dataset usage. To combat this, dataset...

Overlapping Data in Network Protocols: Bridging OS and NIDS Reassembly Gap

IPv4, IPv6, and TCP have a common mechanism allowing one to split an original data packet into several chunks. Such chunked packets may have overlapping data portions and, OS network stack implementations may reassemble these overlaps differently. A Network Intrusion Detection System NIDS that...

New Linux Rootkit

Interesting: The company has released a working rootkit called "Curing" that uses iouring, a feature built into the Linux kernel, to stealthily perform malicious activities without being caught by many of the detection solutions currently on the market. At the heart of the issue is the heavy...

Breaking the Flow and the Bank: Stealthy Cyberattacks on Water Network Hydraulics

As water distribution networks WDNs become increasingly connected with digital infrastructures, they face greater exposure to cyberattacks that threaten their operational integrity. Stealthy False Data Injection Attacks SFDIAs are particularly concerning, as they manipulate sensor data to...

Mustang Panda Targets Myanmar With StarProxy, EDR Bypass, and TONESHELL Updates

The China-linked threat actor known as Mustang Panda has been attributed to a cyber attack targeting an unspecified organization in Myanmar with previously unreported tooling, highlighting continued effort by the threat actors to increase the sophistication and effectiveness of their malware. Thi...

Bypassing Prompt Injection and Jailbreak Detection in LLM Guardrails

Large Language Models LLMs guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection and jailbreak detection systems via traditional character...