AIBullisharXiv – CS AI · Jun 87/10
🧠Researchers introduce Zero-Shot Embedding Drift Detection (ZEDD), a lightweight defense mechanism that detects prompt injection attacks on large language models by measuring semantic shifts in embedding space. The method achieves over 93% accuracy with less than 3% false positives across multiple LLM architectures without requiring model access or task-specific training.
🧠 Llama
AIBearisharXiv – CS AI · May 297/10
🧠Researchers have developed a comprehensive taxonomy of jailbreak attacks and defenses for Large Audio Language Models (LALMs), identifying vulnerabilities across semantic, acoustic, signal, and embedding layers. The study reveals that current defenses create tradeoffs between robustness and usability, highlighting the need for cost-aware safety evaluation beyond simple success-rate metrics.
AIBullisharXiv – CS AI · May 97/10
🧠SafeHarbor is a new framework that enhances Large Language Model agent safety by using hierarchical memory and context-aware defense rules to prevent harmful tool use while maintaining utility on benign tasks. The system achieves 93%+ refusal rates against malicious requests while preserving 63.6% performance on legitimate tasks, addressing a critical trade-off in AI safety.
🧠 GPT-4
AI × CryptoBullisharXiv – CS AI · Mar 56/10
🤖Researchers developed a multi-dimensional quality scoring framework for decentralized LLM inference networks that evaluates output quality across multiple dimensions including semantic quality and query-output alignment. The framework integrates with Proof of Quality (PoQ) mechanisms to provide better incentive alignment and defense against adversarial attacks in distributed AI compute networks.
AIBullisharXiv – CS AI · Mar 47/103
🧠Researchers propose a dual Randomized Smoothing framework that overcomes limitations of standard neural network robustness certification by using input-dependent noise variances instead of global ones. The method achieves strong performance at both small and large radii with gains of 15-20% on CIFAR-10 and 8-17% on ImageNet, while adding only 60% computational overhead.
AINeutralarXiv – CS AI · Jun 116/10
🧠Researchers introduce Robust Privacy (RP), an inference-stage privacy framework that leverages certified robustness principles to prevent adversaries from inferring sensitive attributes or reconstructing training data from model predictions. The approach significantly outperforms differential privacy methods, reducing model inversion attack success rates from 73% to 4% while maintaining 98.4% accuracy, though it remains vulnerable to function-level extraction through model distillation.
AINeutralarXiv – CS AI · Jun 26/10
🧠Researchers introduce Fair Fine-tuning (FFt), a defense mechanism that combines fairness constraints with model fine-tuning to mitigate distribution inference attacks, where adversaries infer sensitive demographic information from machine learning models. The approach reduces adversarial accuracy gaps from ~15% to under 4% across multiple datasets while providing formal theoretical guarantees linking fairness metrics to privacy protection.
🏢 Meta
AINeutralarXiv – CS AI · May 276/10
🧠Researchers propose a dynamic defense mechanism for Multi-Agent Systems that identifies and isolates malicious agents by computing each agent's contribution to final outputs through backward propagation. The method addresses a critical vulnerability where adversarial agents can inject false information that spreads through agent networks, improving security for LLM-based multi-agent applications.
