Tag

#security

25 articles tagged #security

arxiv1d ago

Advancing the State-of-the-Art in Empirical Privacy Auditing

arXiv:2606.10481v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning of large language models (LLMs) can exhibit problematic memorization of individual training examples. Empirical privacy auditing (EPA) quantifies this risk by measuring realistic data leakage on membership inference (M

#privacy #language-models #auditing Read on arxiv →

arxivJun 1

LLM Anonymization Against Agentic Re-Identificatio

arXiv:2605.30848v1 Announce Type: cross Abstract: Agentic LLMs with web search change the threat model for text anonymization: weak contextual cues can become cross-referenceable evidence for re-identification, yet those same details also carry downstream analytic value of the text. Existing defense

AU1 model #anonymization #privacy #security Read on arxiv →

arxivMay 29bullish

WaterSearch: A Quality-Aware Search-based Watermarking Framework for Large Language Models

arXiv:2512.00837v2 Announce Type: replace Abstract: Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated content. Exi

LA1 model #watermarking #language-models #security Read on arxiv →

arxivMay 29bullish

AliMark: Enhancing Robustness of Sentence-Level Watermarking Against Text Paraphrasing

arXiv:2605.29434v1 Announce Type: cross Abstract: Existing sentence-level watermarking methods enhance robustness to paraphrasing by anchoring watermarks in sentence semantics. However, their prefix-based designs remain vulnerable to structural perturbations, such as sentence splitting and merging,

DIOP2 models #watermarking #paraphrasing #robustness Read on arxiv →

arxivMay 22bullish

Heartbeat-Bound Hierarchical Credentials: Cryptographic Revocation for AI Agent Swarms

arXiv:2605.20704v1 Announce Type: cross Abstract: Autonomous AI agents that spawn sub-agent swarms create a safety gap: existing credential revocation mechanisms, OAuth~2.0 introspection, OCSP, and W3C Status Lists, require network connectivity to a central authority, leaving ``zombie agents'' execu

GP1 model #cryptography #security #multiagent Read on arxiv →

openaiMay 18bullish

OpenAI and Dell partner to bring Codex to hybrid and on-premise enterprise environments

OpenAI and Dell partner to bring Codex to hybrid and on-premise environments, helping enterprises deploy AI coding agents securely across data and workflows.

CO1 model #partnership #enterprise #security Read on openai →

arxivMay 16

Trapping Attacker in Dilemma: Examining Internal Correlations and External Influences of Trigger for Defending GNN Backdoors

arXiv:2605.08278v2 Announce Type: replace-cross Abstract: GNNs have become a standard tool for learning on relational data, yet they remain highly vulnerable to backdoor attacks. Prior defenses often depend on inspecting specific subgraph patterns or node features, and thus can be circumvented by ad

#graph-neural-networks #backdoor-attacks #security Read on arxiv →

arxivMay 16bearish

Capacitive Touchscreens at Risk: Recovering Handwritten Trajectory on Smartphone via Electromagnetic Emanations

arXiv:2512.11484v1 Announce Type: cross Abstract: This paper reveals and exploits a critical security vulnerability: the electromagnetic (EM) side channel of capacitive touchscreens leaks sufficient information to recover fine-grained, continuous handwriting trajectories. We present Touchscreen Elec

#security #vulnerability #attack Read on arxiv →

arxivMay 11

Searching for Privacy Risks in LLM Agents via Simulation

arXiv:2508.10880v3 Announce Type: replace-cross Abstract: The widespread deployment of LLM-based agents is likely to introduce a critical privacy threat: malicious agents that proactively engage others in multi-turn interactions to extract sensitive information. However, the evolving nature of such

LL1 model #privacy #security #language-models Read on arxiv →

arxivMay 8bullish

Addressing Labelled Data Scarcity: Taxonomy-Agnostic Annotation of PII Values in HTTP Traffic using LLMs

arXiv:2605.06305v1 Announce Type: new Abstract: Automated privacy audits of web and mobile applications often analyse outbound HTTP traffic to detect Personally Identifiable Information (PII) leakage. However, existing learning-based detectors typically depend on scarce, manually labelled traffic an

LA1 model #privacy #security #annotation Read on arxiv →

arxivMay 8

SMI: Statistical Membership Inference for Reliable Unlearned Model Auditing

arXiv:2602.01150v2 Announce Type: replace-cross Abstract: Machine unlearning (MU) is essential for enforcing the right to be forgotten in machine learning systems. A key challenge of MU is how to reliably audit whether a model has truly forgotten specified training data. Membership Inference Attacks

#machine-learning #unlearning #auditing Read on arxiv →

arxivMay 6

E-MIA: Exam-Style Black-Box Membership Inference Attacks against RAG Systems

arXiv:2605.00955v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) equips large language models (LLMs) with external evidence by retrieving documents at inference time, but it also turns the retrieval corpusinto a sensitive asset. Under a black-box setting, an adversary given a c

RE1 model #security #language-models #inference Read on arxiv →

arxivMay 5

Semia: Auditing Agent Skills via Constraint-Guided Representation Synthesis

arXiv:2605.00314v1 Announce Type: cross Abstract: An agent skill is a configuration package that equips an LLM-driven agent with a concrete capability, such as reading email, executing shell commands, or signing blockchain transactions. Each skill is a hybrid artifact-a structured half declares exec

LL1 model #security #audit #llm Read on arxiv →

arxivMay 1bullish

From surveillance to signalling: escalation channels as environmental controls for agentic AI

arXiv:2510.05192v2 Announce Type: replace-cross Abstract: When AI agents operating with access to sensitive information encounter a conflict between completing an assigned task and following rules or ethical constraints, they can resort to unsanctioned behaviour. Existing inference time safety work

LL1 model #safety #security #ai ethics Read on arxiv →

arxivApr 24

Unveiling Unicode's Unseen Underpinnings in Undermining Authorship Attribution

arXiv:2508.15840v5 Announce Type: replace-cross Abstract: When using a public communication channel--whether formal or informal, such as commenting or posting on social media--end users have no expectation of privacy: they compose a message and broadcast it for the world to see. Even if an end user

#security #steganography #stylometry Read on arxiv →

arxivApr 23

Atomic Decision Boundaries: A Structural Requirement for Guaranteeing Execution-Time Admissibility in Autonomous Systems

arXiv:2604.17511v2 Announce Type: replace-cross Abstract: Autonomous systems increasingly execute actions that directly modify shared state, creating an urgent need for precise control over which transitions are permitted to occur. Existing governance mechanisms evaluate policies prior to execution

#governance #autonomous-systems #security Read on arxiv →

arxivApr 22

Owner-Harm: A Missing Threat Model for AI Agent Safety

arXiv:2604.18658v1 Announce Type: cross Abstract: Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own deployers. Real-wor

AGAGLL3 models #safety #security #benchmark Read on arxiv →

arxivApr 22

Evaluating LLM-Generated Obfuscated XSS Payloads for Machine Learning-Based Detection

arXiv:2604.19526v1 Announce Type: cross Abstract: Cross-site scripting (XSS) remains a persistent web security vulnerability, especially because obfuscation can change the surface form of a malicious payload while preserving its behavior. These transformations make it difficult for traditional and m

LA1 model #security #obfuscation #machine-learning Read on arxiv →

arxivApr 21bearish

The Blind Spot of Agent Safety: How Benign User Instructions Expose Critical Vulnerabilities in Computer-Use Agents

arXiv:2604.10577v2 Announce Type: replace-cross Abstract: Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit thre

CL1 model #safety #security #benchmark Read on arxiv →

arxivApr 17

Between a Rock and a Hard Place: The Tension Between Ethical Reasoning and Safety Alignment in LLMs

arXiv:2509.05367v4 Announce Type: replace-cross Abstract: Large Language Model safety alignment predominantly operates on a binary assumption that requests are either safe or unsafe. This classification proves insufficient when models encounter ethical dilemmas, where the capacity to reason through

#safety #security #cryptography Read on arxiv →

arxivApr 16

Fully Homomorphic Encryption on Llama 3 model for privacy preserving LLM inference

arXiv:2604.12168v1 Announce Type: cross Abstract: The applications of Generative Artificial Intelligence (GenAI) and their intersections with data-driven fields, such as healthcare, finance, transportation, and information security, have led to significant improvements in service efficiency and low

DE1 model #security #cryptography #homomorphic-encryption Read on arxiv →

arxivApr 11

Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection

arXiv:2604.07831v1 Announce Type: cross Abstract: Existing red-teaming studies on GUI agents have important limitations. Adversarial perturbations typically require white-box access, which is unavailable for commercial systems, while prompt injection is increasingly mitigated by stronger safety alig

#security #adversarial #computer-vision Read on arxiv →

arxivApr 10bearish

CAAP: Capture-Aware Adversarial Patch Attacks on Palmprint Recognition Models

arXiv:2604.06987v1 Announce Type: cross Abstract: Palmprint recognition is deployed in security-critical applications, including access control and palm-based payment, due to its contactless acquisition and highly discriminative ridge-and-crease textures. However, the robustness of deep palmprint re

#security #adversarial-attacks #computer-vision Read on arxiv →

arxivApr 6

Learning the Signature of Memorization in Autoregressive Language Models

arXiv:2604.03199v1 Announce Type: cross Abstract: All prior membership inference attacks for fine-tuned language models use hand-crafted heuristics (e.g., loss thresholding, Min-K\%, reference calibration), each bounded by the designer's intuition. We introduce the first transferable learned attack,

MARWRE3 models #membership inference #language models #transfer learning Read on arxiv →

thevergeApr 2bearish

PSA: Anyone with a link can view your Granola notes by default

If you use the AI-powered note-taking app Granola, you might want to double-check your privacy settings. Though Granola says your notes are "private by default," it makes them viewable to anyone with a link, and also uses them for internal AI training unless you opt out. Granola describes itself as

GR1 model #privacy #security #ai-training Read on theverge →

Tag