arXiv:2606. 04459v1 Announce Type: cross Abstract: Language model parameters are known to impose unique (to each model) geometric constraints on their logit outputs, which serves as a signature that identifies the model, but also leaks the model's final layer parameters when an API distributes logits.
arXiv:2510. 06732v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used as rerankers in information retrieval, yet their ranking behavior can be steered by small, natural-sounding prompts.
arXiv:2607. 10252v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly consumed through opaque serving chains - API aggregators, resellers, and inference providers - in which the client has no technical means to confirm that the model answering is the model advertised, and recent audits show that a substantial fraction of commercial endpoints deviate from the vendor's reference weights.
The paper investigates the threat of stegomalware—malicious payloads hidden in large language model weights—and explores permutation symmetry as a defense. It demonstrates that carefully chosen permutations can neutralize stegomalware across all weights, unlike prior methods that left many weights untouched. Conversely, the same symmetry can be exploited to embed malware losslessly, without retraining or payload-specific extraction scripts, while only minimally affecting model performance.
arXiv:2603.17170v2 Announce Type: replace-cross Abstract: AI agents increasingly execute users' natural-language (NL) tasks by calling Web services, yet today's Web authorizes these calls through OAu...
arXiv:2511. 00847v5 Announce Type: replace-cross Abstract: The widespread adoption of Large Language Models (LLMs) through Application Programming Interfaces (APIs) induces a critical vulnerability: the potential for dishonest manipulation by service providers.
arXiv:2609.24084v1 Announce Type: cross Abstract: Open-weight large language models (LLMs) can be copied, modified, and redeployed behind black-box APIs, making post-release ownership verification di...
arXiv:2609.00445v1 Announce Type: cross Abstract: Deployed language model safeguards (safety fine-tuning, filtering, unlearning) vary by principal only outside the model weights: filters are reconfig...
The paper proposes a defense against watermark forgery in generative models by randomizing the selection of watermark keys for each query and accepting content only if exactly one key detects a watermark. This approach provides a sample‑count‑independent upper bound on forgery success for blind attackers while preserving model utility. Experiments show a dramatic drop in forgery success rates—from 87% to 1% with four keys for text and from 100% to 2% for images—without significant computational overhead.
arXiv:2606. 15810v1 Announce Type: cross Abstract: Large language models deployed as commercial APIs are vulnerable to model extraction attacks, while existing defenses either act too late or degrade utility for legitimate users.
The paper examines the security challenges of delegating authority to autonomous LLM agents that act on users’ behalf. It introduces a threat model with four adversaries and eight security requirements, demonstrates that current frameworks (LangGraph, CrewAI, AutoGen, MCP) fail to meet these standards, and presents an authorization broker that blocks all identified threats with minimal overhead. The broker is shown to resist numerous attacks and limits compromised sub‑agents to their delegated tasks, and its principles are implemented in VotalAI’s LLM Shield.
arXiv:2607. 01313v1 Announce Type: cross Abstract: In practice, most commercial LLM providers do not publicly release details of underlying LLM architectures.
arXiv:2605. 29524v2 Announce Type: replace-cross Abstract: Relay and reseller APIs increasingly intermediate access to large language models (LLMs), but users have no direct way to verify that a claimed endpoint is actually serving the advertised model.