THE INTERNET IS THINKING
Earlier sources: Security
Digital security protects systems, software, accounts, and information from misuse. Explore cybersecurity, vulnerabilities, threat intelligence, cryptography, privacy, and identity, with links to the underlying advisories and research.
SYMTRI organizes observations from public sources into a living map. Connections reflect shared subject matter; they do not establish causation or endorse a source.
Open in the map ↗645 classified signals in the fourteen-day window. Recent momentum: steady. These counts include signals awaiting readable evidence.
Earlier sources
Up to ten sources with readable evidence, ordered by their feed timestamp. These archive sources can be older than the live fourteen-day window. This list is a sample, not a measure of total activity. Dates distinguish paper publication, repository creation, model/dataset activity, Hacker News posts, and KEV catalog additions. “First archived” records when SYMTRI first stored the signal.
- OpenAlex · Published · First archived
Image-embedded prompt injection vulnerability of vision-language models in dental radiology: a cross-vendor attack–defense evaluation ↗
Abstract Image-embedded prompt injection—adversarial text rendered into the pixel data of a medical image—is an emerging security threat to vision-language models (VLMs) explored for clinical decision support. In an adversarial stress test using a permissive elicitation prompt, we assessed four production-tier VLMs (GPT-4o, Gemini 2.5 Flash, Claude Sonnet 4.5, MedGemma 4B) on 270 DenTeX dental panoramic radiographs under four attack classes, across 58,320 logged inference calls. All four models were vulnerable, with paired attack success rates (ASR) up to 62.6% (95% CI 58.5–66.7%, GPT-4o) and…
- OpenAlex · Published · First archived
Enhancing security in LLM applications: a performance evaluation of early detection systems ↗
Abstract Prompt injection (PI) attacks threaten novel software applications, which have LLM-based functionality. Prompt leakage, a variant of prompt injection, constitutes a serious confidentiality risk to those applications. Existing defenses against PI attacks currently cannot identify prompt leaks precisely. Moreover, an attacker can construct leakage attacks, which could evade most of these defenses. This prevents the ubiquitous adoption of LLMs in software applications. Meanwhile, there is a lack of practical investigations into the effectiveness of prompt injection (PI) detection tools.…
- Europe PMC · Published · First archived
The role of social white matter tracts in susceptibility to phishing in aging. ↗
Vulnerability to fraud and financial exploitation among older adults is an increasing public health concern. Growing evidence supports that cognitive and socioemotional changes with age contribute to greater exploitation risk among older adults, while the neural mechanisms of heightened susceptibility to deception in aging are not well understood. Of note, white matter tracts are particularly impacted in aging and are likely implicated in deception detection. This study, for the first time, examined the extent to which age-related differences in white matter pathways subserving social cognitio
- Hacker News · Posted on Hacker News · First archived
Access open‑weight, cyber‑capable models with one API key ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
Anything connected to the internet is going to get hacked to pieces ↗
Hacker News discussion.
- GitHub · Repository created · First archived
p3374/GhostCam ↗
Stream your phone camera to your own PC from anywhere (4G/5G) and write it to disk in real time. Nothing stored on the phone. End-to-end encrypted, single Windows exe.
- GitHub · Repository created · First archived
pavlenkosa/wayvoice ↗
Offline voice typing for Linux/Wayland. Press a hotkey, speak, and text appears in the active application. Local Whisper • GTK/libadwaita • No cloud required.
- Hacker News · Posted on Hacker News · First archived
Turning Cluely into Malware ↗
Hacker News discussion.
- Hacker News · Posted on Hacker News · First archived
When AI Finds the Bugs We Missed: A Busy Year for MariaDB Security ↗
Hacker News discussion.
- arXiv · Published · First archived
Unitary complexity in polynomial space ↗
We show that if quantum commitments exist, then either there is no polynomial-time solution to the unitary synthesis problem, or $\mathsf{BPP} \neq \mathsf{NEXP}$. Thus, showing unconditionally that quantum commitments exist would require answering at least one of two longstanding open questions in complexity theory. We prove our main result as a consequence of a more general lemma, which shows that every unitary in $\mathsf{unitaryPSPACE}$ either cannot be synthesized efficiently relative to any classical oracle, or can be synthesized efficiently with an oracle for $\mathsf{NEXP}$ search prob…
Live window recorded . This is the ingestion observation time, not the publication or discovery date of each source.
How to assess evidence about Security
Check each original source for its methods, release status, limitations, and supporting data. A repository announcement, a preprint, and a published study provide different kinds of evidence. SYMTRI’s subject classification helps discovery; it does not independently validate the source’s claims.
See the collection and counting methodology ↗ · Read the weekly synthesis ↗
Follow a thread
Explore related regions
These navigation suggestions are part of the map’s editorial structure, rather than measured evidence of a connection.