Beyond End-to-End Recovery: Towards a Better Understanding of LLM Steganography via Rolewise Decomposition
In large language model (LLM) steganography, an encoder hides a private message in an otherwise ordinary response, as te
#cs.CL
共收录 424 条相关情报。
← 返回所有主题Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM Systems
Modern LLM agents can retrieve information from accessible documents, and then disclose a sensitive conclusion assembled
VX-One: Typed, Calibrated Decision Heads for Real-Time Perimeter Triage - An empirical study of unknown-attack honesty, cascade gray zones, and calibration under drift
Perimeter triage faces a latency/semantics trade-off: signature engines are fast and format-safe but blind to unseen att
Protection Is Not One Event: A Survey of RAG Protection Research by Measured Endpoint
Retrieval-augmented generation (RAG) systems face security, privacy, and copyright risks including content leakage, sour
Beyond Binary Labels: Diagnostic Evaluation of LLM Safety with Prompt-Level Rubrics
Current LLM safety benchmarks predominantly rely on binary safe or unsafe labels, lacking explanatory depth and sufferin
Combining Long-Term Memory and LLMs Comes at a High Cost: From Prompt Injection to Persistent Compromise
The widespread adoption of generative artificial intelligence in recent years has brought a parallel rise in prompt inje
CALLIOPE: Private Insights into AI Use, Without Embeddings
We introduce CALLIOPE, a top-down framework for discovering topic hierarchies in large corpora of unstructured data (e.g
MAS-Guard: Unified Guardrails from Individual Agents to Multi-Agent LLM Systems
Agentic AI extends large language models (LLMs) from generating responses to planning and executing complex workflows, s
Disclosure Begets Disclosure: A Self-Reinforcing Privacy Loop in LLM Agents with Persistent Memory
Large language model (LLM) agents increasingly use persistent memory to personalize responses, and personal attributes i
Contextual Candour: Role-Aware Graduated Disclosure for LLMs over Mixed-Sensitivity Contexts
LLMs increasingly operate over mixed-sensitivity contexts, where they must reason over information ranging from public t
Global Security Blind Spots: Translation as a Safety Bypass in Low-Resource Languages
Large language models are deployed globally, yet safety alignment and evaluation remain concentrated in English: harmful
Profile-DP: Differential Privacy for User-Controlled Profile Release in Personalized LLM Inference
Personalized large language models (LLMs) increasingly rely on profile-conditioned inference, pairing public requests wi
Game of Phones: Harnessing Game Theory and LLMs in 'Bot Wars' to Counteract Phone Scams
Phone scams impose substantial and growing costs on individuals and financial systems worldwide, yet existing countermea
Beyond Attack Success Rate: Cost-Aware Metric for Evaluating Iterative LLM Jailbreaks
Attack success rate (ASR) evaluates jailbreaks against large language models without accounting for repeated calls to th
Budgeted Attack Scheduling for LLM Red-Teaming: The Roles of Static Priors, Semantic Guidance, and Online Feedback
As jailbreak attacks against large language models (LLMs) become increasingly diverse, red-teaming has come to rely on l
Policy Is Not Capability: Some Safety Benchmarks Measure Which Definition of "Unsafe" You Trained On
A guardrail classifier is reported as if unsafe were a property of text. It is not: it is a property of a policy, and th
SoK: PIAtlas: Decomposing the Unbounded Prompt Injection Attack Space
Prompt injection is the dominant security risk for large-language-model (LLM) applications and agents, yet the field sti
Peer Pressure: Execution-Verified Co-Evolution of Attacker and Defender Populations for Code Security
LLM code agents increasingly ship code with little oversight, yet defenders trained on static vulnerability datasets fal
The One-Pixel of Reasoning: One Truthful Relation Is Enough to Mislead LLM Agents
Can one sentence manipulate an agent's belief by targeting a single implicit warrant linking evidence to a conclusion? I
The Missing Compliance Class: LLM Graders That Collapse Jailbreak Success, and a Free Check
Jailbreak papers report an attack success rate, the share of responses that deliver the harmful request, and read it as