Full Text Available
Access Full Text at Repository
Search Results - "ArXiv cs.IT Recent Papers"
Search alternatives:
- papers »
-
Trade-off Functions for DP-SGD with Subsampling based on Random Shuffling: Tight Upper and Lower Bounds
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…ArXiv cs.CR Recent Papers…”
Get full text
Online Article RSS Article -
Profiling for Pennies: Unveiling the Privacy Iceberg of LLM Agents
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…ArXiv cs.CR Recent Papers…”
Get full text
-
ClawGuard: Out-of-Band Detection of LLM Agent Workflow Hijacking via EM Side Channel
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…ArXiv cs.CR Recent Papers…”
Get full text
-
Stateful Agent Backdoor
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…ArXiv cs.CR Recent Papers…”
Get full text
-
Secure Seed-Based Multi-bit Watermarking for Diffusion Models from First Principles
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…ArXiv cs.CR Recent Papers…”
Get full text
-
Safety Anchor: Defending Harmful Fine-tuning via Geometric Bottlenecks
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…ArXiv cs.CR Recent Papers…”
Get full text
-
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…ArXiv cs.CR Recent Papers…”
Get full text
-
Heimdallr: Characterizing and Detecting LLM-Induced Security Risks in GitHub CI Workflows
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…ArXiv cs.CR Recent Papers…”
Get full text
-
Backdoor Mitigation in Object Detection via Adversarial Fine-Tuning
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…ArXiv cs.CR Recent Papers…”
Get full text
-
ActiveFlowMark: Assessing Tor Anonymity under Active Bandwidth Watermarking
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…ArXiv cs.CR Recent Papers…”
Get full text
-
SkillScope: Toward Fine-Grained Least-Privilege Enforcement for Agent Skills
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…ArXiv cs.CR Recent Papers…”
Get full text
-
LoopTrap: Termination Poisoning Attacks on LLM Agents
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…ArXiv cs.CR Recent Papers…”
Get full text
-
LeakDojo: Decoding the Leakage Threats of RAG Systems
Published in ArXiv cs.CR Recent Papers (2026)Subjects: “…ArXiv cs.CR Recent Papers…”
Get full text
-
EMO: Pretraining Mixture of Experts for Emergent Modularity
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…ArXiv cs.CL Recent Papers…”
Get full text
-
Beyond Negative Rollouts: Positive-Only Policy Optimization with Implicit Negative Gradients
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…ArXiv cs.CL Recent Papers…”
Get full text
-
StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…ArXiv cs.CL Recent Papers…”
Get full text
-
Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…ArXiv cs.CL Recent Papers…”
Get full text
-
Cited but Not Verified: Parsing and Evaluating Source Attribution in LLM Deep Research Agents
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…ArXiv cs.CL Recent Papers…”
Get full text
-
Parser agreement and disagreement in L2 Korean UD: Implications for human-in-the-loop annotation
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…ArXiv cs.CL Recent Papers…”
Get full text
-
MASPO: Joint Prompt Optimization for LLM-based Multi-Agent Systems
Published in ArXiv cs.CL Recent Papers (2026)Subjects: “…ArXiv cs.CL Recent Papers…”
Get full text