pith. machine review for the scientific record. sign in

archive

Every paper Pith has read. Search by title, abstract, or pith.

1326 papers in cs.CR · page 1

  1. cs.CR 2026-05-14 reviewed
    Length alone triggers LLM backdoors to leak secrets

    MetaBackdoor: Exploiting Positional Encoding as a Backdoor Attack Surface in LLMs

    Ahmed Salem +4

  2. cs.CR 2026-05-14 reviewed
    The paper builds a 507-leaf taxonomy of LLM inference attacks from 932 recent security…

    Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks

    Alexey A. Shvets +3

  3. cs.CR 2026-05-14 reviewed
    Privacy audits need no retraining runs

    Privacy Auditing with Zero (0) Training Run

    Aur\'elien Bellet +3

  4. cs.LG 2026-05-14 reviewed
    SAM worsens DRL backdoors while other fixes reduce them

    Angel or Demon: Investigating the Plasticity Interventions' Impact on Backdoor Threats in Deep Reinforcement Learning

    Chunyi Zhou +6

  5. cs.CR 2026-05-14 reviewed
    Nearly 39% of LLM defense sequences worsen original risks

    Defenses at Odds: Measuring and Explaining Defense Conflicts in Large Language Models

    Chuanchao Zang +7

  6. cs.CR 2026-05-14 reviewed
    Disguised compliance rules let attackers hijack LLM agents

    Exploiting LLM Agent Supply Chains via Payload-less Skills

    Xing Hu +3

  7. cs.LG 2026-05-14 reviewed
    Guardrails adapt from sparse noisy failures via conservative induction

    LiSA: Lifelong Safety Adaptation via Conservative Policy Induction

    Bharath Chandrasekhar +8

  8. cs.NI 2026-05-14 reviewed
    I2P mixes peers randomly across countries

    Geographic Patterns in I2P Peer Selection: An Empirical Network Topology Analysis

    Jacques Bou Abdo +3

  9. cs.SE 2026-05-14 reviewed
    Multi-agent system automates full library fuzzing lifecycle

    FuzzAgent: Multi-Agent System for Evolutionary Library Fuzzing

    Fengyi Wu +5

  10. cs.CR 2026-05-14 reviewed
    Lineage tracking blocks poisoned memory from justifying agent actions

    MemLineage: Lineage-Guided Enforcement for LLM Agent Memory

    Ciyan Ouyang +1

  11. cs.CR 2026-05-14 reviewed
    Jailbreak ASR drops up to 30 points on repeat attempts

    The Great Pretender: A Stochasticity Problem in LLM Jailbreak

    Cong Chen +2

  12. cs.CV 2026-05-14 reviewed
    Diffusion models uncover semantic attacks on vehicle maps

    Systematic Discovery of Semantic Attacks in Online Map Construction through Conditional Diffusion

    Chenyi Wang +7

  13. cs.CR 2026-05-14 reviewed
    Model forensics verifies AI integrity in wireless networks

    Model Forensics in AI-Native Wireless Networks: Taxonomy, Applications, and Case Study

    Dusit Niyato +6

  14. cs.CR 2026-05-14 reviewed
    Hidden noise stops vision-language models learning real content

    To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model

    Chengshuai Zhao +4

  15. cs.CR 2026-05-14 reviewed
    Web agents should plan before seeing page content

    Web Agents Should Adopt the Plan-Then-Execute Paradigm

    Annabella Chow +7

  16. cs.LG 2026-05-14 reviewed
    MetaMoE combines independently trained expert models into one Mixture-of-Experts system…

    MetaMoE: Diversity-Aware Proxy Selection for Privacy-Preserving Mixture-of-Experts Unification

    Shuhao Chen +2

  17. cs.GT 2026-05-14 reviewed
    Watermarks can be added to game strategies with bounded utility loss

    Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games

    Fei Fang +2

  18. cs.CR 2026-05-14 reviewed
    Encrypted controllers still allow covert attacks

    On the (non-)resilience of encrypted controllers to covert attacks

    Janis Adamek +2

  19. cs.CR 2026-05-14 reviewed
    Bots micro-pace to evade 97% of ICS detectors

    Characterizing AI-Assisted Bot Traffic in Darknet Data: Implications for ICS and IIoT Security

    Alex Carbajal +4

  20. eess.SY 2026-05-13 reviewed
    Endogenous trust cuts misinformation impact by 91% above threshold

    Day-to-Day Traffic Network Modeling under Route-Guidance Misinformation: Endogenous Trust and Resilience in CAV Environments

    Eunhan Ka +1

  21. cs.NI 2026-05-13 reviewed
    Fingerprinting blocks RRC storms in 5G O-RAN before exhaustion

    StormShield: Fingerprint-Based Detection and Mitigation of RRC Signaling Storms in O-RAN 5G RANs

    Andrea Lacava +6

  22. quant-ph 2026-05-13 reviewed
    Survey maps three types of backdoor threats in variational quantum circuits

    Backdoor Threats in Variational Quantum Circuits: Taxonomy, Attacks, and Defenses

    Fan Chen +1

  23. cs.CR 2026-05-13 reviewed
    Small rotations hide data in embeddings undetected

    VectorSmuggle: Steganographic Exfiltration in Embedding Stores and a Cryptographic Provenance Defense

    Jascha Wanger

  24. cs.CR 2026-05-13 reviewed
    Client committee speeds secure aggregation 4.6x

    DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning

    Anastasios Drosou +6

  25. cs.CR 2026-05-13 reviewed
    Canary tokens link scrapers to the LLMs they feed

    Identifying AI Web Scrapers Using Canary Tokens

    Caroline Zhang +5

  26. cs.CR 2026-05-13 reviewed
    FALCON signatures secure MQTT on Raspberry Pi 5 with performance costs

    MQTT Across a Raspberry Pi 5 IoT Network Utilizing Quantum-resistant Signature Algorithms

    Chansu Yu +1

  27. cs.CR 2026-05-13 reviewed
    EBCC unifies TEE enclaves with standard OCI container lifecycle

    EBCC: Enclave-Backed Confidential Containers via OCI-Compatible Runtime Integration

    Di Lu +6

  28. cs.CR 2026-05-13 reviewed
    Thresholding captures most gains of personalized DP budgets

    Limits of Personalizing Differential Privacy Budgets

    Edwige Cyffers +1

  29. cs.RO 2026-05-13 reviewed
    Refinement cuts UAV localization error in cold starts and against faults

    Uncertainty-Aware 3D Position Refinement for Multi-UAV Systems

    Damir Pulatov +1

  30. cs.CR 2026-05-13 reviewed
    EMI creates phantom forces in robot tactile sensors

    Phantom Force: Injecting Adversarial Tactile Perceptions into Embodied Intelligence via EMI

    Sze Yiu Chau +2

  31. cs.CR 2026-05-13 reviewed
    Sleeper channels let inputs attack AI agents later

    Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents

    Dmitry Namiot +1

  32. cs.CR 2026-05-13 reviewed
    External skill library keeps LLM attacks evolving after saturation

    Model-Agnostic Lifelong LLM Safety via Externalized Attack-Defense Co-Evolution

    Bingyu Yan +6

  33. cs.CR 2026-05-13 reviewed
    GA attack makes reasoning models output 26x more text

    Inducing Overthink: Hierarchical Genetic Algorithm-based DoS Attack on Black-Box Large Language Reasoning Models

    Hui Xue +6

  34. cs.CR 2026-05-13 reviewed
    Context vectors raise SIEM attack detection F1 to 0.967

    Context-Aware Web Attack Detection in Open-Source SIEM Systems via MITRE ATT&CK-Enriched Behavioral Profiling

    Aref Shaheed +4

  35. cs.CR 2026-05-13 reviewed
    Tool finds 545 reference counting bugs in Linux kernel drivers

    Automatic Detection of Reference Counting Bugs in Linux Kernel Drivers

    Joe Hattori +2

  36. cs.CR 2026-05-13 reviewed
    Backdoors hide as ordinary latent directions in neural nets

    Backdoor Channels Hidden in Latent Space: Cryptographic Undetectability in Modern Neural Networks

    Eirik Reiestad +3

  37. cs.AR 2026-05-13 reviewed
    PoisonCap gives CHERI strict use-after-free at zero overhead

    PoisonCap: Efficient Hierarchical Temporal Safety for CHERI

    Alexandre Joannou +7

  38. cs.CR 2026-05-13 reviewed
    Spectral truncation secures models and adapters without retraining

    LoREnc: Low-Rank Encryption for Securing Foundation Models and LoRA Adapters

    Beomjin Ahn +3

  39. cs.CR 2026-05-13 reviewed
    Lightweight ML detects IoT intrusions at 99% on microcontrollers

    Empowering IoT Security: On-Device Intrusion Detection in Resource Constrained Devices

    Aftab Khan +5

  40. cs.SE 2026-05-13 reviewed
    Code models miss over 93% of fixes from changes alone

    Code-Centric Detection of Vulnerability-Fixing Commits: A Unified Benchmark and Empirical Study

    Felix M\"achtle +4

  41. cs.CR 2026-05-13 reviewed
    Transfers disguised as ordinary DeFi losses evade tracing

    Extending Blockchain Untraceability with Plausible Deniability

    Eunchan Park +4

  42. cs.CR 2026-05-13 reviewed
    Compromised PRNG forces exact images from diffusion models

    DiffusionHijack: Supply-Chain PRNG Backdoor Attack on Diffusion Models and Quantum Random Number Defense

    Liling Zheng +3

  43. quant-ph 2026-05-13 reviewed
    Contract checks catch sneaky quantum overrides in hybrid pipelines

    QCIVET: A Quantum--Classical Pipeline Integrity Framework with Contract-Based Subtype Verification and Hash-Chained Audit Traces

    Esra Yeniaras +1

  44. cs.CR 2026-05-13 reviewed
    Bonuses for security scans cut issue density in team code

    Security Incentivization: An Empirical Study of how Micropayments Impact Code Security

    Alexander Lercher +7

  45. cs.CR 2026-05-13 reviewed
    Watermarking turns into entity monitoring via output aggregation

    Watermarking Should Be Treated as a Monitoring Primitive

    Jie Zhang +2

  46. cs.CR 2026-05-13 reviewed
    Fuzzing finds 30% of agent skills break their own safety rules

    No Attack Required: Semantic Fuzzing for Specification Violations in Agent Skills

    Hanzhi Liu +5

  47. cs.CR 2026-05-13 reviewed
    Attack extracts AMD EPYC root seed to forge any attestation

    Insecure Despite Proven Updated: Extracting the Root VCEK Seed on EPYC Milan via a Software-Only Attack

    Muyan Shen +1

  48. cs.CR 2026-05-13 reviewed
    IAM Canary Roles top cloud beacon attribution scores

    CLOUDBURST: Cloud-Layer Observations Using Beacons for Unified Real-time Surveillance and Threat Attribution

    Abraham Itzhak Weinberg

  49. cs.CR 2026-05-13 reviewed
    Subpopulation bias marks distilled datasets for black-box tracing

    From Compression to Accountability: Harmless Copyright Protection for Dataset Distillation

    Joey Tianyi Zhou +4

  50. cs.CR 2026-05-13 reviewed
    Thermal cameras fingerprint VR apps remotely

    ThermalTap: Passive Application Fingerprinting in VR Headsets via Thermal Side Channels

    A H M Nazmus Sakib +5