Unlocking User-Oriented Pages: Intention-Driven Black-Box Scanner for Real-World Web Applications

Black-box scanners have played a significant role in detecting vulnerabilities for web applications. A key focus in current black-box scanning is increasing test coverage i.e., accessing more web pages. However, since many web applications are user-oriented, some deep pages can only be accessed...

AGATE: Stealthy Black-Box Watermarking for Multimodal Model Copyright Protection

Recent advancement in large-scale Artificial Intelligence AI models offering multimodal services have become foundational in AI systems, making them prime targets for model theft. Existing methods select Out-of-Distribution OoD data as backdoor watermarks and retrain the original model for...

Graph of Attacks: Improved Black-Box and Interpretable Jailbreaks for LLMs

The challenge of ensuring Large Language Models LLMs align with societal standards is of increasing interest, as these models are still prone to adversarial jailbreaks that bypass their safety mechanisms. Identifying these vulnerabilities is crucial for enhancing the robustness of LLMs against su...

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,...

Q-FAKER: Query-Free Hard Black-Box Attack Via Controlled Generation

Many adversarial attack approaches are proposed to verify the vulnerability of language models. However, they require numerous queries and the information on the target model. Even black-box attack methods also require the target model's output information. They are not applicable in real-world...

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...

Token-Level Constraint Boundary Search for Jailbreaking Text-To-Image Models

Recent advancements in Text-to-Image T2I generation have significantly enhanced the realism and creativity of generated images. However, such powerful generative capabilities pose risks related to the production of inappropriate or harmful content. Existing defense mechanisms, including prompt...

CVE-2022-4636

Black Box KVM Firmware version 3.4.31307 on models ACR1000A-R-R2, ACR1000A-T-R2, ACR1002A-T, ACR1002A-R, and ACR1020A-T is vulnerable to path traversal, which may allow an attacker to steal user credentials and other sensitive information through local file inclusion...

CloudBrute - Awesome Cloud Enumerator

A tool to find a company target infrastructure, files, and apps on the top cloud providers Amazon, Google, Microsoft, DigitalOcean, Alibaba, Vultr, Linode. The outcome is useful for bug bounty hunters, red teamers, and penetration testers alike. The complete writeup is available. here Motivation ...

Radamsa - A General-Purpose Fuzzer

Radamsa is a test case generator for robustness testing, a.k.a. a fuzzer. It is typically used to test how well a program can withstand malformed and potentially malicious inputs. It works by reading sample files of valid data and generating interestringly different outputs from them. The main...

Researchers Highlight Google's Gemini AI Susceptibility to LLM Threats

Google's Gemini large language model LLM is susceptible to security threats that could cause it to divulge system prompts, generate harmful content, and carry out indirect injection attacks. The findings come from HiddenLayer, which said the issues impact consumers using Gemini Advanced with Goog...

Top 10 web application vulnerabilities in 2021–2023

To help companies with navigating the world of web application vulnerabilities and securing their own web applications, the Open Web Application Security Project OWASP online community created the OWASP Top Ten. As we followed their rankings, we noticed that the way we ranked major vulnerabilitie...

The Internet Is Turning Into a Data Black Box. An ‘Inspectability API’ Could Crack It Open

Unlike web browsers, mobile apps increasingly make it difficult or impossible to see what companies are really doing with your data. The answer? An inspectability API...

Firefly - Black Box Fuzzer For Web Applications

Firefly is an advanced black-box fuzzer and not just a standard asset discovery tool. Firefly provides the advantage of testing a target with a large number of built-in checks to detect behaviors in the target. Note: Firefly is in a very new stage v1.0 but works well for now, if the target does n...

GHSA-86H2-2G4G-29QX avo possible unsafe reflection / partial DoS vulnerability

Summary The polymorphic field type stores the classes to operate on when updating a record with user input, and does not validate them in the back end. This can lead to unexpected behavior, remote code execution, or application crashes when viewing a manipulated record. Details After reviewing th...

Design/Logic Flaw

OpenSIPS is a Session Initiation Protocol SIP server implementation. Prior to versions 3.1.7 and 3.2.4, OpenSIPS crashes when a malformed SDP body is received and is processed by the deletesdpline function in the sipmsgops module. This issue can be reproduced by calling the function with an SDP...

CVE-2022-4636

Black Box KVM Firmware version 3.4.31307 on models ACR1000A-R-R2, ACR1000A-T-R2, ACR1002A-T, ACR1002A-R, and ACR1020A-T is vulnerable to path traversal, which may allow an attacker to steal user credentials and other sensitive information through local file inclusion...

CVE-2022-4636

Black Box KVM Firmware version 3.4.31307 on models ACR1000A-R-R2, ACR1000A-T-R2, ACR1002A-T, ACR1002A-R, and ACR1020A-T is vulnerable to path traversal, which may allow an attacker to steal user credentials and other sensitive information through local file inclusion...

Path traversal

Black Box KVM Firmware version 3.4.31307 on models ACR1000A-R-R2, ACR1000A-T-R2, ACR1002A-T, ACR1002A-R, and ACR1020A-T is vulnerable to path traversal, which may allow an attacker to steal user credentials and other sensitive information through local file inclusion...

CVE-2022-4636

Affected Product: Black Box KVM Firmware v3.4.31307 for models ACR1000A-R-R2, ACR1000A-T-R2, ACR1002A-T, ACR1002A-R, ACR1020A-T. Vulnerability: path traversal via local file inclusion (CWE-22) allowing an attacker to access credentials and sensitive data. Root cause: improper validation of pathna...