arxiv5d agobullish
arXiv:2607.19351v1 Announce Type: new Abstract: LLM-based multi-agent systems (LLM-MAS) are increasingly deployed in safety-critical applications, where adversaries inject malicious instructions through inter-agent communication to propagate harmful behaviors. Unlike static threats, these attacks ar
arxiv5d ago
arXiv:2607.19432v1 Announce Type: cross Abstract: The Model Context Protocol (MCP) is an open-source standard that allows AI agents to connect to external tools, databases, and services. While this connectivity enables powerful agent capabilities, it also introduces multi-step attacks that existing
techcrunch5d ago
As Chinese AI models grow in capability and popularity among U.S. companies, the arguing over what should be done about them has reached a fever pitch.
arxivJul 10
arXiv:2607.07775v1 Announce Type: new Abstract: The human body is at the center of a growing family of technologies designed to tightly and persistently couple biological and digital systems. Robotic prostheses are a representative example of this tight coupling. Also referred to as bionic limbs, ro
arxivJul 2
arXiv:2601.14660v2 Announce Type: replace-cross Abstract: Agentic Large Language Models (LLMs) are models able to reason, plan, and execute tools over unstructured data. These abilities are enabling transformative applications in domains spanning from personal assistant, financial, and legal domains
arxivJun 27
arXiv:2606.26793v1 Announce Type: cross Abstract: Multimodal agentic retrieval-augmented generation (RAG) systems expand the attack surface beyond prompt injection to include text poisoning, image injection, direct-query attacks, and orchestrator-level tool manipulation. Existing red-teaming approac
arxivJun 26
arXiv:2606.26707v1 Announce Type: cross Abstract: Adversarial APKs are Android applications modified in the problem space to evade machine-learning malware detectors. In this work, we first show that, despite claims, existing problem-space attacks remain largely impractical. Most techniques leverage
techcrunchJun 19
Just as last week was ending, the US government forced Anthropic to pull its two newest models, Fable 5 and Mythos 5, citing national security concerns after Amazon researchers allegedly found a way to bypass Fable 5’s guardrails. Cybersecurity researchers have since signed an open letter calling th
arxivJun 18
arXiv:2606.18996v1 Announce Type: cross Abstract: Agents are increasingly deployed in document-intensive workflows where sensitive private information is not an edge case but a routine input, e.g., an agent booking a flight needs passport numbers. In such settings, the agent must use private informa
arxivJun 18
arXiv:2606.18532v1 Announce Type: cross Abstract: AI systems are increasingly evaluated in bounded environments that combine isolation, simulation, instrumentation, supervision, and evidence capture. For physical AI, AIoT, and cyber-physical systems, this shift is not a matter of terminology: the sy
arxivJun 17
arXiv:2604.01904v3 Announce Type: replace-cross Abstract: Post-hoc unauthorized-training data detection for large language models (LLMs) typically assumes a query-with-originals regime: rights holders query a target LLM with raw proprietary data and assess whether the model assigns them stronger mem
arxivJun 15bearish
arXiv:2512.02318v4 Announce Type: replace-cross Abstract: This paper studies how multimodal large language models (MLLMs) undermine the security guarantees of visual CAPTCHA. We identify the attack surface where an adversary can cheaply automate CAPTCHA solving using off-the-shelf models. We evaluat
arxivJun 12
arXiv:2606.12737v1 Announce Type: cross Abstract: Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt injection attacks through untrusted external sources. Existing defenses
arxivJun 12
arXiv:2606.12075v1 Announce Type: cross Abstract: Network Intrusion Detection Systems (NIDS) heavily utlize Machine Learning (ML) but ML models can be manipulated via adversarial attacks. These attacks add carefully crafted perturbations to network traffic data that leads to misclassifications. Whil
arxivJun 12bearish
arXiv:2606.13385v1 Announce Type: cross Abstract: Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments, where they operate over untrusted web content and execute actions with direct consequences. This makes them vulnerable to prompt-injection attacks
arxivJun 11
arXiv:2606.11505v1 Announce Type: cross Abstract: Biometric systems are increasingly deployed in security applications; however, they remain vulnerable to spoofing attacks, in which attackers exploit counterfeit biometric data to gain unauthorized access. This research evaluates the effectiveness of
arxivJun 10
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
arxivJun 1
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
arxivMay 29bullish
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
arxivMay 29bullish
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,
arxivMay 22bullish
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
openaiMay 18bullish
OpenAI and Dell partner to bring Codex to hybrid and on-premise environments, helping enterprises deploy AI coding agents securely across data and workflows.
arxivMay 16
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
arxivMay 16bearish
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
arxivMay 11
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
arxivMay 8bullish
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
arxivMay 8
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
arxivMay 6
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
arxivMay 5
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
arxivMay 1bullish
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
arxivApr 24
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
arxivApr 23
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
arxivApr 22
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
arxivApr 22
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
arxivApr 21bearish
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
arxivApr 17
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
arxivApr 16
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
arxivApr 11
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
arxivApr 10bearish
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
arxivApr 6
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,
thevergeApr 2bearish
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