Cryptography & Security
Research on AI security, adversarial attacks, privacy, and cryptographic methods.
cs.CR · 505 papersBackdoor Threats in Variational Quantum Circuits: Taxonomy, Attacks, and Defenses
This paper surveys backdoor attacks in Variational Quantum Circuits (VQCs), detailing their taxonomy, attack mechanisms, and defense strategies.
VectorSmuggle: Steganographic Exfiltration in Embedding Stores and a Cryptographic Provenance Defense
VectorSmuggle reveals steganographic data exfiltration in RAG embedding stores and proposes VectorPin, a cryptographic defense for embedding integrity.
DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning
DisAgg uses distributed client aggregators to securely and efficiently aggregate updates in federated learning, achieving a 4.6x speedup over OPA.
Identifying AI Web Scrapers Using Canary Tokens
This paper introduces a novel method using canary tokens to reliably identify which web scrapers are feeding data to specific large language models.
MQTT Across a Raspberry Pi 5 IoT Network Utilizing Quantum-resistant Signature Algorithms
This paper explores implementing quantum-resistant FALCON signatures on MQTT IoT networks using Raspberry Pi 5 to secure devices.
EBCC: Enclave-Backed Confidential Containers via OCI-Compatible Runtime Integration
EBCC integrates TEE-backed confidential containers with standard OCI runtimes, simplifying management of secure workloads.
Limits of Personalizing Differential Privacy Budgets
This paper reveals that personalized differential privacy budgets have significant limitations, showing a simple thresholding method is often superior.
Uncertainty-Aware 3D Position Refinement for Multi-UAV Systems
This paper introduces a decentralized, uncertainty-aware 3D position refinement layer for multi-UAV systems, improving localization robustness.
Phantom Force: Injecting Adversarial Tactile Perceptions into Embodied Intelligence via EMI
This paper reveals how electromagnetic interference can inject "phantom forces" into robot tactile sensors, severely compromising embodied intelligence.
Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents
Persistent prompt injection in always-on AI agents via 'sleeper channels' is identified, and a tiered defense with provenance gates is proposed.
Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution
EvoSafety introduces a novel framework for lifelong, model-agnostic LLM safety via externalized attack-defense co-evolution to counter adversarial prompts.
Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models
A hierarchical genetic algorithm can induce "overthink" in black-box LLMs, creating DoS attacks by significantly increasing response length and resource consumption.
Context-Aware Web Attack Detection in Open-Source SIEM Systems via MITRE ATT&CK-Enriched Behavioral Profiling
Smart-SIEM enhances open-source SIEMs with an AI module for context-aware web attack detection using behavioral profiling and MITRE ATT&CK.
Automatic Detection of Reference Counting Bugs in Linux Kernel Drivers
DrvHorn automatically detects reference counting bugs in Linux kernel drivers, finding 545 bugs (424 new) with a low false positive rate.
Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks
This paper shows how to create cryptographically undetectable backdoors in modern neural networks by exploiting latent space geometry, resisting current defenses.
PoisonCap: Efficient Hierarchical Temporal Safety for CHERI
PoisonCap enhances CHERI systems with strict use-after-free and initialization safety using a novel 'poison' capability format, without performance overhead.
LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters
LoREnc is a training-free framework that secures foundation models and LoRA adapters against IP leakage and model recovery attacks with minimal overhead.
Empowering IoT Security: On-Device Intrusion Detection in Resource Constrained Devices
A lightweight ML model enables high-accuracy, on-device intrusion detection for resource-constrained IoT, protecting against common cyber threats.
Code-Centric Detection of Vulnerability-Fixing Commits: A Unified Benchmark and Empirical Study
This study finds code language models struggle to detect vulnerability-fixing commits without commit messages, lacking transferable security understanding from code changes alone.
Extending Blockchain Untraceability with Plausible Deniability
This paper introduces Deniable Covert Asset Transfer (DCAT) to make blockchain transactions untraceable by blending them into common DeFi MEV activities.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.