CVE-2021-44228-white-box

Article Journal: https://www.researchgate.net/publication/373214720PengujianKerentananpadaCVE-2021-44228terhadapAncamanRemoteAccessTrojan Thesis: https://1drv.ms/b/s!Al-8jtgY0iBXmz79DKEROaZT5n8a?e=1E6Pkm Log4Shell // n. Log4j Vulnerability Environment Box This repo purposely built for Log4j...

CVE-2022-44877-white-box

Docs Paper : https://docs.google.com/document/d/1rQ7e9i2AFzHbASfRu3nkgjIswbrS2AB2i7V9OK3dJLs/edit?usp=sharing Libprochider : https://github.com/gianlucaborello/libprocesshider /var/www/html YouTube Demo : https://www.youtube.com/watch?v=V0HgzE8IElA&t=343s tested machine box CentOS 7 - CentOS Web...

Cobra

Cobra This project's design can no longer meet current white-box scanning requirements. It is no longer maintained and is intended for research use only. Please do not use it in a production environment. Introduction Cobra is a source code security audit tool that supports detecting most prominen...

gradient-untangler

gradient-untangler A local research harness that searches for the exact tokens that make an open-weight language model start its answer the way you specify. Open-weight models ship as ordinary files: config.json, a tokenizer, and one or more .safetensors or .bin shards. A Hugging Face id is only ...

promptmap

O O o.-. ¡Humanos, no os resistáis! |/ ,-'-. / /, / /|.-.| / --O-- .--"""/\ /\ | o.o / De Utku Sen /|\ -'--' / /| | - | / | | | \ /| | | ' \ '/ \ ' | ' \ | ' / | ' \ | / | | | ./| /|| | ./| || , | .// / / |-----| || | | || || promptmap2 es un escáner automatizado de inyección de instrucciones par...

AgentXploit: Autonomous Repository-To-Runtime Red-Teaming for AI Agents

AI agents combine language models with external data and tools that can modify files, call APIs, or execute code. Security failures can arise when adversarial content changes an agent's tool use or when the surrounding software contains vulnerabilities such as path traversal or command injection...

ENDOPROMPT: Victim-Side Pseudo-References for Utility Degradation

Prompt injection can degrade benign task performance without eliciting harmful content. Yet many attack objectives depend on task labels or predefined target responses. We present ENDOPROMPT, a white-box method that learns utility-degrading prefixes from unlabeled instructions. Its generator take...

Divide and Doubt: Diverse Distributed Poisoning for Retrieval-Augmented Generation

Multi-passage corpus poisoning often repeats one target claim across similar documents, creating correlated lexical and semantic patterns that similarity- and conflict-aware defenses can suppress jointly. We introduce DnD Divide and Doubt, a targeted attack based on two principles: distributing...

NeuronFuzz: Safety Neuron Guided Fuzzing for LLM Safety Evaluation

Safety evaluation is critical for assessing whether aligned Large Language Models LLMs remain robust against jailbreak attacks. Existing automated testing methods, however, largely rely on response-level feedback: each candidate prompt typically requires generating a target-model response to...

crucible

Crucible AI-Driven Automated Vulnerability Verification Pla...

MissClick: Exploiting Digit-Serialized Coordinates to Attack GUI Grounding Models

Recent GUI visual grounding models generate screen coordinates as sequences of digit tokens that are parsed into numerical values and mapped to executable clicks. The security implications of this coordinate generation process have been largely overlooked. We observe that each coordinate digit is...

AI Forensics across White-, Grey-, and Black-Box Access: A Process Model and Research Agenda for Post-Incident Investigation of AI Systems

AI systems are increasingly involved in decisions and actions that may later require investigation. When an AI related incident occurs, investigators need to reconstruct what the system did, why it behaved that way, and which part of the system or supply chain contributed to the outcome. Existing...

When Cheap Gradients Fail: The Measurement Cost of Attacking Quantum Classifiers

Adversarial perturbations threaten machine learning classifiers, including variational quantum classifiers. We show that finite quantum measurement statistics shot noise act as a built-in defense against gradient-based test-time attacks whose cost scales unfavorably for the attacker. Because ever...

Statistically Undetectable Backdoors in Deep Neural Networks

We show how an adversarial model trainer can plant backdoors in a large class of deep, feedforward neural networks. These backdoors are statistically undetectable in the white-box setting, meaning that the backdoored and honestly trained models are close in total variation distance, even given th...

DroidBreaker: Practical and Functional Problem-Space Attacks on Machine-Learning Android Malware Detectors

Adversarial APKs are Android applications modified in the problem space to evade machine-learning malware detectors. In this work, we first show that, despite claims, existing problem-space attacks remain largely impractical. Most techniques leverage software transplantation to inject entire beni...

Assessing Automated Prompt Injection Attacks in Agentic Environments

Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effective for jailbreaking--remain underexplored in realistic agentic settings. We present a comprehensive empirical evaluation of automated prompt...

MRMMIA: Membership Inference Attacks on Memory in Chat Agents

Membership inference attacks MIAs test whether a target data record belongs to a system's private data, and have become a standard tool to measure privacy leakage in machine learning systems. Prior work has primarily focused on training corpora or retrieval databases. However, MIAs against agent...

Re-Triggering Safeguards within LLMs for Jailbreak Detection

This paper proposes a jailbreaking prompt detection method for large language models LLMs to defend against jailbreak attacks. Although recent LLMs are equipped with built-in safeguards, it remains possible to craft jailbreaking prompts that bypass them. We argue that such jailbreaking prompts ar...

Attention Is Where You Attack

Safety-aligned large language models rely on RLHF and instruction tuning to refuse harmful requests, yet the internal mechanisms implementing safety behavior remain poorly understood. We introduce the Attention Redistribution Attack ARA, a white-box adversarial attack that identifies...

Towards Optimal Agentic Architectures for Offensive Security Tasks

Agentic security systems increasingly audit live targets with tool-using LLMs, but prior systems fix a single coordination topology, leaving unclear when additional agents help and when they only add cost. We treat topology choice as an empirical systems question. We introduce a controlled...