Entries tagged security
Filters: Type: entry × security × Sorted by date
Prompt injection and jailbreaking are not the same thing
I keep seeing people use the term “prompt injection” when they’re actually talking about “jailbreaking”.
[... 1157 words]Weeknotes: Page caching and custom templates for Datasette Cloud
My main development focus this week has been adding public page caching to Datasette Cloud, and exploring what custom template support might look like for that service.
[... 924 words]Recommendations to help mitigate prompt injection: limit the blast radius
I’m in the latest episode of RedMonk’s Conversation series, talking with Kate Holterhoff about the prompt injection class of security vulnerabilities: what it is, why it’s so dangerous and why the industry response to it so far has been pretty disappointing.
[... 539 words]Prompt injection explained, November 2023 edition
A neat thing about podcast appearances is that, thanks to Whisper transcriptions, I can often repurpose parts of them as written content for my blog.
[... 1357 words]Multi-modal prompt injection image attacks against GPT-4V
GPT4-V is the new mode of GPT-4 that allows you to upload images as part of your conversations. It’s absolutely brilliant. It also provides a whole new set of vectors for prompt injection attacks.
[... 889 words]Delimiters won’t save you from prompt injection
Prompt injection remains an unsolved problem. The best we can do at the moment, disappointingly, is to raise awareness of the issue. As I pointed out last week, “if you don’t understand it, you are doomed to implement it.”
[... 1010 words]Prompt injection explained, with video, slides, and a transcript
I participated in a webinar this morning about prompt injection, organized by LangChain and hosted by Harrison Chase, with Willem Pienaar, Kojin Oshiba (Robust Intelligence), and Jonathan Cohen and Christopher Parisien (Nvidia Research).
[... 3120 words]The Dual LLM pattern for building AI assistants that can resist prompt injection
I really want an AI assistant: a Large Language Model powered chatbot that can answer questions and perform actions for me based on access to my private data and tools.
[... 2547 words]Prompt injection: What’s the worst that can happen?
Activity around building sophisticated applications on top of LLMs (Large Language Models) such as GPT-3/4/ChatGPT/etc is growing like wildfire right now.
[... 2302 words]Datasette 0.64, with a warning about SpatiaLite
I release Datasette 0.64 this morning. This release is mainly a response to the realization that it’s not safe to run Datasette with the SpatiaLite extension loaded if that Datasette instance is configured to enable arbitrary SQL queries from untrusted users.
[... 675 words]You can’t solve AI security problems with more AI
One of the most common proposed solutions to prompt injection attacks (where an AI language model backed system is subverted by a user injecting malicious input—“ignore previous instructions and do this instead”) is to apply more AI to the problem.
[... 1234 words]I don’t know how to solve prompt injection
Some extended thoughts about prompt injection attacks against software built on top of AI language models such a GPT-3. This post started as a Twitter thread but I’m promoting it to a full blog entry here.
[... 581 words]s3-credentials: a tool for creating credentials for S3 buckets
I’ve built a command-line tool called s3-credentials to solve a problem that’s been frustrating me for ages: how to quickly and easily create AWS credentials (an access key and secret key) that have permission to read or write from just a single S3 bucket.
[... 1618 words]Exploring the SameSite cookie attribute for preventing CSRF
In reading Yan Zhu’s excellent write-up of the JSON CSRF vulnerability she found in OkCupid one thing puzzled me: I was under the impression that browsers these days default to treating cookies as SameSite=Lax, so I would expect attacks like the one Yan described not to work in modern browsers.
Weeknotes: New releases across nine different projects
A new release and security patch for Datasette, plus releases of sqlite-utils, datasette-auth-passwords, django-sql-dashboard, datasette-upload-csvs, xml-analyser, datasette-placekey, datasette-mask-columns and db-to-sqlite.
[... 861 words]Datasette 0.51 (plus weeknotes)
I shipped Datasette 0.51 today, with a new visual design, plugin hooks for adding navigation options, better handling of binary data, URL building utility methods and better support for running Datasette behind a proxy. It’s a lot of stuff! Here are the annotated release notes.
[... 2020 words]Weeknotes: datasette-ics, datasette-upload-csvs, datasette-configure-fts, asgi-csrf
I’ve been preparing for the NICAR 2020 Data Journalism conference this week which has lead me into a flurry of activity across a plethora of different projects and plugins.
[... 834 words]Single sign-on against GitHub using ASGI middleware
I released Datasette 0.29 last weekend, the first version of Datasette to be built on top of ASGI (discussed previously in Porting Datasette to ASGI, and Turtles all the way down).
[... 1612 words]Is there anyway to game unique link verifications? Like when you get sent a link of the form https:/........com/UID=TYYN04001 How would one change the digits to reproduce another working link?
Not if they’ve been implemented correctly.
[... 42 words]How could GitHub improve the password security of its users?
By doing exactly what they’re doing already: adding more sophisticated rate limiting, and preventing users from using common weak passwords.
[... 80 words]What steps can I take to protect my data in case my laptop gets stolen?
Set up full drive encryption—that way if someone steals your laptop they won’t be able to access your data without a password.
[... 95 words]I would like to setup a web-server which will be used solely by myself. What would be the safest way to do so in terms of confidentiality of the contents?
I haven’t configured them myself, but it might be worth looking in to client SSL certificates for this. That way your server won’t communicate with any browser that hasn’t installed a certificate which you generate. I believe the BBC used to use this for a lot of their important servers which they wanted to be accessible only by their own developers from across the internet (I don’t know if they still do).
[... 108 words]What are the best practices to avoid XSS and SQL Injections attacks (platform agnostic)?
Input validation is, in my opinion, a red herring. Sure—if you ask the user for an integer or date you should make sure they entered one before attempting to save it anywhere or use it for processing, but injection attacks often involve text fields (e.g. names, or comments posted on Quora) and validating those on input is a recipe for banning “Tim O’Reilly” from ever creating a proper profile on your site!
[... 316 words]Why would someone browse the web with JavaScript disabled?
Security conscious users (who understand the implications of XSS and CSRF attacks) sometimes disable JavaScript completely, or use a tool like the NoScript extension to disable it for all sites and only re-enable it on a small whitelist of sites that they trust.
[... 67 words]What are the JSON security concerns in web development?
Be very careful when implementing JSON-P for authenticated actions—evil third party sites could assemble URLs to your user’s private data and steal it. This attack has worked against Gmail in the past.
[... 203 words]Why do browsers allow cross-domain JavaScript to execute but not XMLHttpRequests?
It’s called the Same Origin Policy, and it’s principally about intranets. Imagine you have a URL http://intranet.corp/top-secret-...—and you then visit http://evil.example.com/ . If cross domain XHR was allowed the evil site could suck that secret document off your intranet without you realising.
[... 105 words]Why do some websites implement their logout link as a form post via JavaScript versus a plain old GET request?
Probably because if you implement logout as a GET action, I can force you to log out of a site by tricking you in to visiting a page with an <img src="http://yoursite.com/logout/" width="1" height="1"> element on it.
[... 64 words]Why are XSS attacks spreading like fire these days?
XSS attacks are common and easy, and crop up all the time. What’s new is that the number of people who are aware of the potential for XSS worms has increased hugely, so when an XSS does crop up in something popular there’s a much higher chance of someone turning it in to a worm (as happened with Twitter the other day).
[... 96 words]