AI in the Browser - Revision history

Tom: /* Assets to Protect */

2025-06-15T19:46:39Z

‎Assets to Protect

Tom: /* Context */

2025-06-15T19:39:29Z

‎Context

Tom: /* Assets to Protect */

2025-06-15T19:38:06Z

‎Assets to Protect

Tom: /* Assets to Protect */

2025-06-15T19:36:48Z

‎Assets to Protect

Tom: /* Context */

2025-06-15T19:33:33Z

‎Context

Tom: /* User Profiling */

2025-06-06T23:08:25Z

‎User Profiling

Tom: /* Problems */

2025-06-06T23:01:24Z

‎Problems

Tom: /* References */

2025-04-09T19:13:30Z

‎References

Tom: /* References */

2025-04-09T19:10:12Z

‎References

Tom: /* Full Title */

2025-02-10T19:37:08Z

‎Full Title

@@ Line 9: / Line 9: @@
 Google and the other browser developers have been trying to make web apps, that are downloaded from web sites, as attractive and useful as native apps, that are downloaded from the app store. Now that AI access is getting added to the browser it is important to look at the impact on the user.  The following is a quote from the introduction of one API to Chromium. We can expect more APIs enabling access to AI soon.<blockquote>Browsers and operating systems are increasingly expected to gain access to a language model. By exposing this built-in model, we avoid every website needing to download their own multi-gigabyte language model, or send input text to third-party APIs. The rewriter API in particular exposes a high-level API for interfacing with a language model in order to transform inputs for a variety of use cases, in a way that does not depend on the specific language model in question.  https://github.com/explainers-by-googlers/writing-assistance-apis/blob/main/README.md#rewriter-api</blockquote>
 ===Assets to Protect===
-The assets to be protected are the components and information that are essential to the functioning and purpose of a [[User Experience]] application (like [[Browser]]s and similar [[User Agent]]s) and the supporting infrastructure.
+The assets to be protected are the components and information that are essential to the functioning and purpose of a [[User Experience]] application (like [[Browser]]s and similar scriptable [[User Agent]]s) and the supporting infrastructure.
 These assets can be categorized as

@@ Line 9: / Line 9: @@
 Google and the other browser developers have been trying to make web apps, that are downloaded from web sites, as attractive and useful as native apps, that are downloaded from the app store. Now that AI access is getting added to the browser it is important to look at the impact on the user.  The following is a quote from the introduction of one API to Chromium. We can expect more APIs enabling access to AI soon.<blockquote>Browsers and operating systems are increasingly expected to gain access to a language model. By exposing this built-in model, we avoid every website needing to download their own multi-gigabyte language model, or send input text to third-party APIs. The rewriter API in particular exposes a high-level API for interfacing with a language model in order to transform inputs for a variety of use cases, in a way that does not depend on the specific language model in question.  https://github.com/explainers-by-googlers/writing-assistance-apis/blob/main/README.md#rewriter-api</blockquote>
 ===Assets to Protect===
-The assets to be protected are the components and information that are essential to the functioning and purpose of a [[User Experience]] application (like browsers and similar [[User Agent]]s) and the supporting infrastructure.
+The assets to be protected are the components and information that are essential to the functioning and purpose of a [[User Experience]] application (like [[Browser]]s and similar [[User Agent]]s) and the supporting infrastructure.
 These assets can be categorized as

@@ Line 9: / Line 9: @@
 Google and the other browser developers have been trying to make web apps, that are downloaded from web sites, as attractive and useful as native apps, that are downloaded from the app store. Now that AI access is getting added to the browser it is important to look at the impact on the user.  The following is a quote from the introduction of one API to Chromium. We can expect more APIs enabling access to AI soon.<blockquote>Browsers and operating systems are increasingly expected to gain access to a language model. By exposing this built-in model, we avoid every website needing to download their own multi-gigabyte language model, or send input text to third-party APIs. The rewriter API in particular exposes a high-level API for interfacing with a language model in order to transform inputs for a variety of use cases, in a way that does not depend on the specific language model in question.  https://github.com/explainers-by-googlers/writing-assistance-apis/blob/main/README.md#rewriter-api</blockquote>
 ===Assets to Protect===
-The assets to be protected are the components and information that are essential to the functioning and purpose of a [[User Experience]] application (like browsers and similar [[User Agents]]) and the supporting infrastructure.
+The assets to be protected are the components and information that are essential to the functioning and purpose of a [[User Experience]] application (like browsers and similar [[User Agent]]s) and the supporting infrastructure.
 These assets can be categorized as

@@ Line 9: / Line 9: @@
 Google and the other browser developers have been trying to make web apps, that are downloaded from web sites, as attractive and useful as native apps, that are downloaded from the app store. Now that AI access is getting added to the browser it is important to look at the impact on the user.  The following is a quote from the introduction of one API to Chromium. We can expect more APIs enabling access to AI soon.<blockquote>Browsers and operating systems are increasingly expected to gain access to a language model. By exposing this built-in model, we avoid every website needing to download their own multi-gigabyte language model, or send input text to third-party APIs. The rewriter API in particular exposes a high-level API for interfacing with a language model in order to transform inputs for a variety of use cases, in a way that does not depend on the specific language model in question.  https://github.com/explainers-by-googlers/writing-assistance-apis/blob/main/README.md#rewriter-api</blockquote>
 ===Assets to Protect===
-In a web threat assessment, the assets to be protected are the components and information that are essential to the functioning and purpose of a web application and its supporting infrastructure.
+The assets to be protected are the components and information that are essential to the functioning and purpose of a [[User Experience]] application (like browsers and similar [[User Agents]]) and the supporting infrastructure.
 These assets can be categorized as

@@ Line 8: / Line 8: @@
 ==Context==
 Google and the other browser developers have been trying to make web apps, that are downloaded from web sites, as attractive and useful as native apps, that are downloaded from the app store. Now that AI access is getting added to the browser it is important to look at the impact on the user.  The following is a quote from the introduction of one API to Chromium. We can expect more APIs enabling access to AI soon.<blockquote>Browsers and operating systems are increasingly expected to gain access to a language model. By exposing this built-in model, we avoid every website needing to download their own multi-gigabyte language model, or send input text to third-party APIs. The rewriter API in particular exposes a high-level API for interfacing with a language model in order to transform inputs for a variety of use cases, in a way that does not depend on the specific language model in question.  https://github.com/explainers-by-googlers/writing-assistance-apis/blob/main/README.md#rewriter-api</blockquote>
 ==Problems==

@@ Line 13: / Line 13: @@
 ===User Profiling===
 The web site will be able to ask the AI loaded on the user's device for a UI that would match what the user would see has the local AI is used in that personal user device. Trying different responses to the same user (via the local AI agent) would give the website information about the user's preferences and behavior. Clearly this is a way to avoid asking the user to share information by trying to extract in from the user's AI without the user's permission or knowledge.
 ===Prompt Injection===

← Older revision		Revision as of 19:13, 9 April 2025
Line 23:		Line 23:

	[[Category: Artificial Intelligence]]		[[Category: Artificial Intelligence]]
		+	[[Category: Article]]
	[[Category: Browser]]		[[Category: Browser]]

@@ Line 22: / Line 22: @@
 ==References==
-[[Category: AI]]
+[[Category: Artificial Intelligence]]
 [[Category: Browser]]

← Older revision		Revision as of 19:37, 10 February 2025
Line 3:		Line 3:

	Author: Tom Jones 2024-09-21		Author: Tom Jones 2024-09-21
		+
		+	* [https://github.com/w3c-cg/threat-modeling/blob/main/models/ai-in-browser.md A more current version might be on GitHub]

	==Context==		==Context==