D-Scan

コンテキストが牙をむくとき：文書レベルの注意崩壊によるRAGポイズニングの検出 D-SCANは、RAG（Retrieval-Augmented Generation）システムにおける文書ポイズニング攻撃を検出するための分析フレームワークです。生成中にLLMの内部状態（トークン確率と注意重み）を収集し、多次元特徴量を抽出し、クリーンな検索文書とポイズニングされた検索文書を区別する分類器を訓練します。 1. インストールと要件 前提条件 Python = 3.9 CUDA対応GPU（8Bパラメータモデルの推論には24GB以上のVRAMを推奨） モデルの準備 このプロジェクトはデフォルトで...

RPP: A Certified Poisoned-Sample Detection Framework for Backdoor Attacks under Dataset Imbalance

Deep neural networks are highly susceptible to backdoor attacks, yet most defense methods to date rely on balanced data, overlooking the pervasive class imbalance in real-world scenarios that can amplify backdoor threats. This paper presents the first in-depth investigation of how the dataset...

An Efficient Anomaly Detection Framework for Wireless Sensor Networks Using Markov Process

Wireless Sensor Networks forms the backbone of modern cyber physical systems used in various applications such as environmental monitoring, healthcare monitoring, industrial automation, and smart infrastructure. Ensuring the reliability of data collected through these networks is essential as the...

JULI: Jailbreak Large Language Models by Self-Introspection

Large Language Models LLMs are trained with safety alignment to prevent generating malicious content. Although some attacks have highlighted vulnerabilities in these safety-aligned LLMs, they typically have limitations, such as necessitating access to the model weights or the generation process...

getRandomTokenIdFromFund yields wrong probabilities for ERC1155

Handle @cmichelio Vulnerability details Vulnerability Details NFTXVaultUpgradeable.getRandomTokenIdFromFund does not work with ERC1155 as it does not take the deposited quantity1155 into account. Impact Assume tokenId0 has a count of 100, and tokenId1 has a count of 1. Then getRandomId would have...