← All posts

Problem-Aware

225 posts on problem-aware.

Does Perplexity Train on Your Data? Consumer, Enterprise, and API Rules

Perplexity applies different model-training rules to consumer accounts, Enterprise products, and its API. Free, Pro, and Max accounts have AI data retention enabled by default but can opt out for future data. Enterprise customer content and API customer content are excluded from model training under current terms. Training, service processing, retention, feedback, and anonymized usage data remain separate review questions.

ai-securityai-governanceperplexitydata-loss-preventionpolicy-enforcement
Read post →

Does Gemini Train on Your Data? Consumer, Workspace, and API Rules

Google applies different data-use rules to consumer Gemini Apps, managed Google Workspace accounts, and the Gemini API. Consumer chats may improve Google AI when Keep Activity is on. Workspace content is not used for generative AI model training outside the domain without permission. Unpaid Gemini API content may be used to improve products, while paid API prompts and responses are excluded from product improvement. This guide maps the product boundaries an enterprise must record before approving Gemini use.

ai-securityai-governancegeminidata-loss-preventionpolicy-enforcement
Read post →

Membership Inference Attacks: The Privacy Signal Hidden in Model Responses

A membership inference attack uses model behavior to estimate whether a specific record appeared in the training data. The privacy harm can exist even when the model reveals no record fields, because membership in a hospital, benefits, or disciplinary dataset can itself disclose sensitive information. This article separates training-time mitigations from the query controls available at an authenticated HTTP model boundary.

ai-securityllm-securitydata-loss-preventionidentity-and-authorizationpolicy-enforcementaudit
Read post →

Does ChatGPT Train on Your Data? The Product Boundary

ChatGPT data use depends on the product and workspace. OpenAI may use content from individual services for model training unless the user opts out. ChatGPT Business, Enterprise, Edu, Healthcare, Teachers, and the API are excluded from training by default. Training settings, retention, memory, and access controls remain separate decisions. This guide maps those boundaries and shows what an enterprise must verify before employees send company data.

ai-securityai-governanceshadow-aidata-loss-preventionpolicy-enforcement
Read post →

AI Security Awareness Training for Employees Using LLMs

AI security awareness training should prepare employees to make specific decisions before a prompt is sent and after an LLM response returns. A role-based program uses realistic exercises for shadow AI, sensitive data, indirect prompt injection, output verification, and escalation, then measures observable behavior instead of attendance.

ai-securityllm-securityprompt-injectionshadow-aipolicy-enforcementcybersecurity
Read post →

EchoLeak: The Zero-Click Copilot Data Leak Explained

EchoLeak, tracked as CVE-2025-32711, showed how an email could place hostile instructions inside Microsoft 365 Copilot retrieval context and turn a trusted answer into a data-exfiltration path. This analysis separates the injection, retrieval, model, rendering, and network boundaries so security teams can assign controls without overstating what any one gateway can see.

prompt-injectionllm-securityai-securitydata-loss-preventionidentity-and-authorization
Read post →

Crescendo Attack: Detect the Conversation, Not One Prompt

A Crescendo attack builds a jailbreak across several benign-looking turns, using the model''s own replies as material for the next escalation. Defending against it requires conversation-aware testing and policy, plus a clear account of what an HTTP gateway can inspect when providers keep server-side state.

ai-securityllm-securityprompt-injectioncybersecuritypolicy-enforcement
Read post →

ASCII Smuggling Hides Instructions in Visible Text

ASCII smuggling uses non-rendering Unicode tag characters that mirror printable ASCII, allowing text to carry a hidden instruction while looking ordinary on screen. Security controls should inspect the raw code points, normalize or reject unexpected tags, constrain model authority, and preserve the original and transformed request evidence.

prompt-injectionllm-securityai-securitypolicy-enforcementcybersecurity
Read post →

Many-Shot Jailbreaking Turns Long Context Into Attack Surface

Many-shot jailbreaking fills a long context with fabricated dialogues in which an assistant repeatedly complies with requests it would normally refuse. The demonstrations steer the model toward compliance on a final harmful request. Production defenses need context-aware testing, request limits, independent policy, and evidence beyond provider refusal behavior.

llm-securityai-securityprompt-injectionllmpolicy-enforcement
Read post →

AI Kill Chain: Put Controls at the Transitions

An AI kill chain maps an adversary operation as transitions across reconnaissance, access, model interaction, execution, collection, and impact. The useful control work happens at those transitions. This guide maps evidence and ownership while keeping HTTP request-boundary enforcement separate from endpoint, identity, and model-development controls.

ai-securityllm-securitycybersecurityagentic-aiinline-enforcementarchitecture
Read post →

AI Incident Database: What Security Teams Can Learn

The AI Incident Database collects public reports of harmful or potentially harmful AI behavior so researchers and practitioners can find recurring failure patterns. Security teams can use it for scenario discovery and control design, while keeping internal incident records, evidence, and reporting decisions in their own governed systems.

ai-securityai-governancecybersecurityforensic-auditaudit
Read post →

Prompt Injection Benchmarks: AgentDojo, BIPIA, CyberSecEval

Seven prompt injection benchmarks are in active use and their headline attack success rates run from 24% to 84.30%: AgentDojo (629 security cases, ETH Zurich, NeurIPS 2024), BIPIA (Microsoft, KDD 2025), InjecAgent (1,054 cases, ACL Findings 2024), Open-Prompt-Injection (USENIX Security 24), CyberSecEval 2 (Meta, 26-41% on every model), Agent Security Bench (ICLR 2025, 84.30% peak), and MCPTox (45 real MCP servers). Every one of those is a static score. When researchers from OpenAI, Anthropic, and Google DeepMind ran adaptive attacks against twelve published defenses, all twelve fell, most above 90%. This piece gives the comparison table, what each benchmark measures, and the design conclusion the numbers force.

prompt-injectionllm-securityai-securityagentic-aiarchitecture
Read post →