Search: “hidden-text”

New AI Attack Hides Malicious Instructions in Normal-Looking Text to Evade Safety Filters

Check Point researchers show crafted prose hides policy-violating instructions that bypass all tested LLM gatekeepers, including GPT-4o mini and Llama Guard 3.

A new prompt-crafting technique embeds malicious payloads inside grammatical, natural-looking text without Base64, invisible Unicode, or obvious encodings, defeating lightweight pre-screening gatekeepers. In testing, all four evaluated gatekeeper models—gpt-4o-mini-2024-07-18, gpt-oss-safeguard:20b, claude-3-haiku-20240307, and llama-guard3:8b—classified the crafted wrappers as safe at a 100% bypass rate across 23 obfuscated prompts. GPT-5 Thinking in high-reasoning mode recovered and acted on the hidden instruction in 17 of 18 tests (~94.4%), often spending over a minute and multiple Python executions. Researchers recommend paraphrasing untrusted input, hardening gatekeeper policies, and applying defense-in-depth controls for agentic deployments.

GBHackers·Sep 11, 05:53 UTC · 5d agoAI safety & security 2 sources

Telegram Desktop Flaw Lets Attackers Steal Chat Messages Through Poisoned HTML Exports

Telegram Desktop XSS in bot inline keyboard buttons let attackers steal chat content from exported HTML archives; patched in 7.0.1.

ExPatch researchers Denis and Aleksander Rostilov found a stored cross-site scripting flaw in Telegram Desktop's HTML export feature, present since version 4.15.1 (March 2024). JavaScript hidden in bot inline keyboard button text executes when a user opens an exported chat HTML file with JavaScript enabled, exposing messages, metadata, and enabling DOM manipulation such as fake verification screens. Fixes shipped in Desktop Beta 6.9.4 (July 3, 2026) and Stable 7.0.1 (July 14, 2026), but previously exported HTML files remain unsafe.

Cyber Security News·Sep 15, 09:47 UTC · 1d agoVulnerability 2 sources

Attackers conceal phishing lures using invisible Unicode characters

Threat actors use invisible Unicode characters (ASCII smuggling) to hide phishing lures and evade email security filters.

Threat actors have adopted the ASCII smuggling technique in phishing campaigns, embedding invisible Unicode characters in emails to conceal malicious lures. The approach is designed to evade email security filters that scan for visible phishing indicators. The report gives no victim counts or named campaigns.

BleepingComputer·Sep 6, 14:23 UTC · 9d agoPhishing & fraud in the wild

Hackers Can Hide Malicious AI Commands Inside Normal English to Bypass Security Filters

Check Point's PuzzleMask technique hides malicious prompts in ordinary English that fast gatekeeper models miss but high-reasoning downstream models execute.

Check Point researchers disclosed PuzzleMask, a technique concealing policy-breaking instructions in natural-language prose without encodings or invisible characters. Fast screening models classified all 23 crafted wrappers as safe, while a high-reasoning model recovered and acted on the hidden instruction in 17 of 18 tests (94.4%). The gap stems from capability imbalance between gatekeeper and target models, with defenses including paraphrasing untrusted input, stricter self-referential wording rules, and output/tool-call monitoring.

Cyber Security News·Sep 11, 07:36 UTC · 5d agoAI safety & security1

Robust Coverless Linguistic Steganography via Sentence Embedding Space with Global Resynchronization

Researchers propose a coverless steganographic framework encoding messages as hierarchical clustering paths in sentence embedding space with a Global Resynchronization Mechanism for robustness.

An arXiv paper proposes encoding secret messages as hierarchical clustering paths in the sentence embedding space rather than token space, improving decoding stability against word- and sentence-level textual perturbations. A Global Resynchronization Mechanism (GRM) reframes variable-length bitstreams as discrete symbols anchored to semantic subspaces to prevent bit-slippage. Experiments show substantial robustness improvements while maintaining embedding capacity and resistance to statistical analysis.

arXiv cs.CR·Sep 4, 10:22 UTC · 12d agoResearch

Novel-reading apps used users' phones to generate fake ad traffic

Help Net Security·Aug 6, 00:00 UTC · Aug 6, 2026Threat actor1

Hidden Prompts Trick AI Into False Email Summaries

Attackers can hide prompts in invisible HTML within emails to manipulate AI email summarizers into producing misleading summaries.

Dark Reading reports that simple HTML invisible to users can manipulate AI-powered email summarizers into generating false or malicious summaries. The technique is a form of prompt injection delivered through hidden email content. It creates risk that decision-makers act on manipulated AI-generated email summaries rather than the actual message content.

Dark Reading·Aug 25, 21:08 UTC · 21d agoAI safety & security

Microsoft Copilot reveals secret input that allowed it to be hacked

Microsoft disclosed a hidden input in Copilot that let attackers steal passwords from users who clicked a crafted link.

Microsoft revealed that Copilot contained a secret, undocumented input parameter that allowed the assistant to be compromised. Attackers could abuse the hidden input to steal passwords when a target clicked a malicious link. The disclosure highlights hidden-parameter risks in widely deployed AI assistants.

Ars Technica · Security·Aug 18, 13:00 UTC · 29d agoAI safety & security in the wild1

Once popular for attacking AI, ASCII smuggling is embraced by spammers

Spammers adopt ASCII smuggling—invisible Unicode tag characters—to evade email filters, with Microsoft Defender detections spiking to 2.5 million per day.

ASCII smuggling hides text in Unicode tag characters (e.g., U+E0041 for "A") that are invisible to humans but readable by LLMs and text processors. The technique gained attention as a stealthy prompt-injection vector and is now used by spammers to obfuscate keywords from email detectors. Microsoft reported Defender for Office smuggling detections jumped from roughly 21,000 per day to over 1.3 million in early February, reaching 2.5 million within four days, before falling sharply in mid-May.

Ars Technica · Security·Sep 4, 17:18 UTC · 11d agoPhishing & fraud

Hiding Prompt Injection in Legal Filing

A judge banned a plaintiff from electronic court filings after hidden prompt-injection text was discovered planted in legal documents.

Bruce Schneier's blog discusses an incident in which hidden prompt-injection instructions were planted inside a legal filing, apparently targeting AI systems that might process court documents. Judge Walter Spader Jr. responded by banning the plaintiff from electronic filings, requiring all future submissions as printed hard copies. Commenters debate whether the tactic could affect future AI-based processing of court records and whether plain-text formats will regain favor.

Schneier on Security·Aug 31, 11:04 UTC · 16d agoAI safety & security in the wild

Rare Not Random Using Token Efficiency for Secrets Scanning

Researcher proposes token efficiency (string length divided by BPE token count) as a better post-regex filter than entropy for secrets scanning, validated on CredData.

The post explores whether Byte-Pair Encoding tokenization can replace Shannon entropy as the primary filter for candidate secrets captured by regex in tools like Gitleaks. It defines 'token efficiency' as string length divided by token count under the cl100k_base tokenizer; secret-like strings such as GitHub tokens tokenize into many small tokens and score low, while natural text scores high. Evaluating labeled secrets from the CredData dataset shows a usable separation, with roughly 2.5 suggested as a minimum cutoff versus Gitleaks' 3.5 entropy threshold. The technique is positioned as a post-regex filtering step rather than a standalone detector.

Lobsters · security·Sep 12, 06:42 UTC · 4d agoResearch

ASCII smuggling isn't just an AI security risk

Microsoft tracked a phishing campaign peaking at 2.37 million daily messages that hid financial-lure keywords with invisible Unicode tag characters to evade filters.

Microsoft researchers uncovered a large phishing campaign that inserted invisible Unicode tag characters (e.g., U+E0020) inside common financial keywords like 'funding', splitting words so keyword, signature, and regex matches fail. The campaign peaked at more than 2.37 million messages in late February 2026, ran from about 150 finance-themed sender domains on a strict weekday-only schedule, and gradually declined to under 20% of peak weekday volume by late March, with residual spikes through mid-June. The technique repurposes ASCII smuggling, normally used for indirect prompt injection against AI assistants, for traditional email phishing evasion. Microsoft advises defenders to strip or fold invisible Unicode code points before content matching and to watch for bulk weekday spikes from churning finance-themed domains.

The Register · Security·Sep 4, 19:23 UTC · 11d agoPhishing & fraud in the wild1

Phishing Campaign Sends Millions of Emails Using Invisible Unicode to Evade Filters

Microsoft warns of a high-volume phishing campaign using invisible Unicode characters to split keywords like 'funding' and evade filters, peaking at 2.37 million daily messages.

Microsoft's Security Research team documented a high-volume phishing operation inserting deprecated Unicode Tags characters (U+E0000-U+E007F) inside financial keywords such as 'funding' so literal-string and regex email filters stop matching them. The campaign ran on a weekly cadence with 1-2.37 million weekday messages between February and May 15, 2026, peaking on February 26, 2026. It used hundreds of disposable finance-themed sender domains and relayed mail through ActiveCampaign's click-tracking infrastructure (acemlnd[.]com, activehosted[.]com), lending legitimate platform reputation. Microsoft ties the activity to an AI-assisted SBA loan phishing campaign that Fortra's FIRE team disclosed in September 2025.

The Hacker News·Sep 4, 15:57 UTC · 11d agoPhishing & fraud in the wild

Augustinian BabyLM: What Ostensive Definition Can and Cannot Teach a Small Language Model

Study shows visually grounded token embeddings in a small masked LM persist through training and improve object-property knowledge, but escape standard BabyLM benchmarks.

The paper implements ostensive definition for a small DeBERTa masked language model trained on 10M words, seeding visually grounded tokens with embeddings derived from labeled image regions before training. Visual initialization leaves a persistent, seed-replicated advantage on object-property knowledge (COMPS) and a corpus-tailored Visual-Property Swap benchmark covering color, material, size, and shape, but has no effect on most BabyLM grammar benchmarks. Synthetic grounding of previously unseeded words causally transfers the advantage to exactly those words.

arXiv cs.AI / cs.LG / cs.CL·Sep 10, 17:43 UTC · 5d agoAI research

Distributed and Private Textual Data Synthesis from Embeddings

Researchers propose a distributed differentially private text synthesis method combining DP summaries and secure protocols, removing the need for a trusted curator.

The paper presents a differential privacy and cryptography co-design for synthesizing textual training data without a trusted curator or tightly synchronized user participation. It releases a one-time DP summary in embedding space, identifying frequent semantic regions and their DP centroids to enable training-free offline text synthesis, with semantic support protection to avoid exposing rare user texts. A custom secure protocol enforces end-to-end DP guarantees over distributed user data. Across four benchmarks the approach achieves utility comparable to the state-of-the-art centralized DP synthesis method.

arXiv cs.CR·Sep 9, 12:33 UTC · 7d agoAI research

Attack hides malware in PNGs and drops custom reverse tunnel on victims' machines

A ClickFix social engineering wave delivers a multi-stage attack that hides malware in PNG files and installs a custom reverse tunnel.

The Register reports a new wave of ClickFix social engineering attacks that trigger a multi-stage infection chain on victim machines. The attack reportedly conceals malware inside PNG image files and deploys a custom reverse tunnel tool for attacker access. Further technical details are limited in the available text.

The Register · Security·Aug 31, 18:26 UTC · 15d agoMalware in the wild

Bad Likert Judge: A Novel Multi-Turn Technique to Jailbreak LLMs by Misusing Their Evaluation Capability

Unit 42 details the Bad Likert Judge multi-turn jailbreak that abuses LLMs' evaluation capability, raising attack success rates over 60% across six frontier models.

Palo Alto Networks Unit 42 describes the Bad Likert Judge technique, a multi-turn jailbreak that asks a target LLM to act as a Likert-scale judge scoring the harmfulness of example responses. The highest-rated example in each scale can carry harmful content, bypassing the model's internal guardrails. Testing across six state-of-the-art text-generation LLMs showed an average attack success rate increase of more than 60% versus plain attack prompts, with tested models anonymized. The technique targets edge cases rather than typical use, and the article positions the work as guidance for defenders on potential jailbreak risks.

Palo Alto Unit 42·Aug 17, 12:34 UTC · Aug 17, 2026AI safety & security

ClickFix Campaigns Abuse Legitimate Services for Persistent Access

Dark Reading reports two ClickFix social engineering campaigns abusing legitimate services to compromise organizations and maintain persistent access.

Dark Reading describes two separate attacks in which threat actors used the ClickFix social engineering tactic to compromise organizations. The campaigns abuse legitimate, trusted services to gain and maintain persistent access to victim environments. No specific victims, actors, or indicators were named in the available text.

Dark Reading·Sep 8, 17:25 UTC · 7d agoThreat actor in the wild

The Shared Clipboard Inside the Sandbox: Cross-Account Data Leakage in ChatGPT

Check Point discovers cross-account data leakage in ChatGPT: isolated code-execution containers communicate via shared JFrog Artifactory, enabling covert Gmail exfiltration.

Check Point Research found a covert bidirectional channel between ChatGPT code-execution containers belonging to different accounts, which were supposed to be isolated from each other and the public internet. Both could reach the same internal JFrog Artifactory instance used for package delivery, whose exposed Item Management API allowed a 'shared clipboard' between containers. In a proof of concept, a hidden instruction in a shared conversation made ChatGPT retrieve email data from the victim's connected Gmail account and send it to the attacker's account while the victim received a normal answer. The same channel could exfiltrate conversation history and session files; OpenAI recently described a similar isolation weakness in its postmortem of the Hugging Face incident.

Check Point Research·Sep 8, 13:00 UTC · 8d agoAI safety & security1

The Hidden Instructions That Can Hijack AI Agents

Hidden prompt injections embedded in documents and metadata can hijack autonomous AI agents, causing data exfiltration and out-of-policy actions at machine speed.

Bowbridge warns that hidden indirect prompt injections, embedded in documents, metadata, emails, images, and code repositories, can cause autonomous AI agents to treat attacker-controlled content as trusted guidance. Because agents inherit user privileges, act silently, and lack human judgment, injections can lead to data exfiltration or file poisoning that traditional security controls cannot detect. A real-world example involved a supplier quote whose metadata instructed an agent to override guidance and select the most expensive option. Bowbridge recommends scanning documents before agents process them.

SecurityWeek·Sep 8, 17:00 UTC · 7d agoAI safety & security

ASCII smuggling crosses over from AI prompt injection to phishing evasion

Microsoft details high-volume phishing campaign using ASCII smuggling (Unicode tag chars) for filter evasion, peaking at 2.3M messages.

Microsoft researchers observed a high-volume finance-themed phishing campaign using invisible Unicode tag characters (U+E0000–U+E007F), a technique known from AI prompt injection research as ASCII smuggling, to split lure words like 'funding' and evade email filters. Telemetry from Microsoft Defender for Office 365 showed signature hits jump from roughly 21,000 messages on February 8, 2026 to more than 1.3 million on February 9, peaking above 2.3 million on February 11, with elevated weekday activity lasting approximately three months. The discovery emerged from prompt injection protection research, showing AI-era evasion techniques crossing into traditional phishing. Most messages were flagged by layered Defender protections rather than a single Unicode-specific signal.

Microsoft Security Blog·Sep 3, 16:00 UTC · 12d agoPhishing & fraud in the wild

InceptionRAG: Stealthy Poisoning Attack Against Retrieval-Augmented Generation

InceptionRAG fragments malicious payloads into dormant passages that trigger LLMs to self-deduce misinformation via multi-hop reasoning, bypassing existing RAG poisoning defenses.

Researchers introduce InceptionRAG, a stealthy corpus poisoning attack against retrieval-augmented generation that splits a malicious payload into a chain of individually harmless dormant passages. When retrieved together, the passages induce LLMs to self-deduce target misinformation through multi-hop reasoning, achieving over 80% attack success rate across three datasets and three LLMs under rigorous adversarial constraints. A zeroth-order suffix optimization (ZOSO) method automates authoritative suffix generation in black-box settings. The authors also propose HODOR, a document isolation defense that decouples adversarial logical dependencies.

arXiv cs.CR·Sep 15, 08:22 UTC · 1d agoResearch

Telegram Desktop XSS Vulnerability Lets Attackers Steal Entire Chat Histories

Stored XSS in Telegram Desktop HTML chat exports (CVSS 8.2) could let attacker-controlled inline keyboard buttons steal full chat histories.

ExPatch researchers Denis and Aleksander Rostilov found a stored XSS in Telegram Desktop's HTML chat export pipeline affecting builds before Beta 6.9.4 and Stable 7.0.1. Unsanitized inline keyboard button text becomes executable JavaScript when a user exports a chat and opens the HTML file in a browser, exposing messages, metadata, and local file paths, and enabling phishing overlays. Telegram patched the issue in commit 8457d13a during July 2026; no CVE had been assigned at disclosure time.

GBHackers·Sep 15, 10:11 UTC · 1d agoVulnerability

I Am No One: Style-Aware Paraphrasing for Text Anonymization

Prompt-driven style-aware paraphrasing with LLMs cuts authorship attribution F1 by 60-70% while preserving content quality.

The paper proposes a style-aware, prompt-driven anonymization approach using pretrained LLMs to build compact stylistic profiles from minimal samples and rewrite text to suppress identifiable style markers while preserving meaning. It addresses stylometric re-identification risks in anonymized text, including ASR transcripts of meetings and call-center calls where leakage persists after acoustic anonymization. Across blog and review datasets, the approach reduces authorship attribution F1 by 60-70%, substantially outperforming both DP-based and non-DP baselines while maintaining readability.

arXiv cs.CR·Sep 11, 02:07 UTC · 5d agoResearch

Telegram Desktop Flaw Could Turn Old Chat Exports Into Data Theft Traps

ExPatch disclosed stored XSS in Telegram Desktop HTML export letting bot messages steal chat data when exports open in browsers.

ExPatch researchers Denis and Aleksander Rostilov found a stored XSS flaw (CVSS 8.2) where bot inline keyboard button text was written unescaped into HTML chat exports, executing attacker JavaScript in browsers. The payload can persist in chat history for months, exfiltrate messages, metadata, and local file paths, and rewrite the page, spreading via forwarded messages without bot membership. Telegram fixed it by applying SerializeString(), first stable fixed release 7.0.1 shipped July 14, 2026, but HTML exports created with vulnerable versions remain dangerous.

Security Affairs·Sep 15, 07:48 UTC · 1d agoVulnerability1· 1 read

Technical Manual for a Toolkit for Measuring Contextual Individuation in Transformer Language Models

An open methodology toolkit measures whether transformer language models contextualize fixed word forms across domains using bridge forms and layer-wise silhouette analysis.

The manual documents an open toolkit built around 'bridge forms' - identical written words recurring across two or more subject domains with a different sense in each - to test whether transformer language models individuate word occurrences by context beyond the embedding layer. It covers declarative specification of bridge forms, Wikipedia corpus acquisition, occurrence localization, layer-wise representation extraction, domain-pairwise silhouette measurement, and visualization, justifying each choice against failure modes such as sense contamination and subword-tokenization misalignment. It is a methodological and implementation reference and reports no empirical results.

arXiv cs.AI / cs.LG / cs.CL·Sep 4, 16:38 UTC · 11d agoAI research

ShieldFont fights AI scraping by handing crawlers the wrong words

Help Net Security·Aug 7, 00:00 UTC · Aug 7, 2026Industry

Grok exfiltrates user data when malicious instructions are encrypted

Researchers show Grok can be made to exfiltrate user data via Cryptographic Context Injection, a newly documented technique that bypasses LLM safety guardrails.

According to Ars Technica, Grok exfiltrates user data when malicious instructions are encrypted, a technique called Cryptographic Context Injection. The method is described as the latest documented way to break LLM safety guardrails, showing that encrypted content can carry hidden instructions past safeguards. The finding underscores gaps in how large language models validate and execute context from external sources.

Ars Technica · Security·Aug 20, 13:00 UTC · 27d agoAI safety & security1