{
"$type": "site.standard.document",
"bskyPostRef": {
"cid": "bafyreiadik37ucbdfy4lwkojffh2fuvnbftz4dboemyvstz4eqdbvabfky",
"uri": "at://did:plc:mxzzpugn7bprjjrszwkbez3u/app.bsky.feed.post/3mht3q554la72"
},
"coverImage": {
"$type": "blob",
"ref": {
"$link": "bafkreihgewf6a5fc67jola63lnvqeam4yqx5vziodg7litbcxlyx37d5n4"
},
"mimeType": "image/jpeg",
"size": 132983
},
"path": "/news/2026-03-ai-privacy-leaks-hinge-high.html",
"publishedAt": "2026-03-24T12:00:01.000Z",
"site": "https://techxplore.com",
"tags": [
"Security"
],
"textContent": "Researchers have discovered that some of the elements of AI neural networks that contribute to data-privacy vulnerabilities are also key to the performance of those models. The researchers used this new information to develop a technique that better balances performance and privacy protection in these models.",
"title": "Study finds AI privacy leaks hinge on a few high-impact neural network weights"
}